Science.gov

Sample records for object recognition system

  1. Cognitive object recognition system (CORS)

    NASA Astrophysics Data System (ADS)

    Raju, Chaitanya; Varadarajan, Karthik Mahesh; Krishnamurthi, Niyant; Xu, Shuli; Biederman, Irving; Kelley, Troy

    2010-04-01

    We have developed a framework, Cognitive Object Recognition System (CORS), inspired by current neurocomputational models and psychophysical research in which multiple recognition algorithms (shape based geometric primitives, 'geons,' and non-geometric feature-based algorithms) are integrated to provide a comprehensive solution to object recognition and landmarking. Objects are defined as a combination of geons, corresponding to their simple parts, and the relations among the parts. However, those objects that are not easily decomposable into geons, such as bushes and trees, are recognized by CORS using "feature-based" algorithms. The unique interaction between these algorithms is a novel approach that combines the effectiveness of both algorithms and takes us closer to a generalized approach to object recognition. CORS allows recognition of objects through a larger range of poses using geometric primitives and performs well under heavy occlusion - about 35% of object surface is sufficient. Furthermore, geon composition of an object allows image understanding and reasoning even with novel objects. With reliable landmarking capability, the system improves vision-based robot navigation in GPS-denied environments. Feasibility of the CORS system was demonstrated with real stereo images captured from a Pioneer robot. The system can currently identify doors, door handles, staircases, trashcans and other relevant landmarks in the indoor environment.

  2. Method and System for Object Recognition Search

    NASA Technical Reports Server (NTRS)

    Duong, Tuan A. (Inventor); Duong, Vu A. (Inventor); Stubberud, Allen R. (Inventor)

    2012-01-01

    A method for object recognition using shape and color features of the object to be recognized. An adaptive architecture is used to recognize and adapt the shape and color features for moving objects to enable object recognition.

  3. A Neural Network Object Recognition System

    DTIC Science & Technology

    1990-07-01

    useful for exploring different neural network configurations. There are three main computation phases of a model based object recognition system...segmentation, feature extraction, and object classification. This report focuses on the object classification stage. For segmentation, a neural network based...are available with the current system. Neural network based feature extraction may be added at a later date. The classification stage consists of a

  4. A neuromorphic system for video object recognition.

    PubMed

    Khosla, Deepak; Chen, Yang; Kim, Kyungnam

    2014-01-01

    Automated video object recognition is a topic of emerging importance in both defense and civilian applications. This work describes an accurate and low-power neuromorphic architecture and system for real-time automated video object recognition. Our system, Neuormorphic Visual Understanding of Scenes (NEOVUS), is inspired by computational neuroscience models of feed-forward object detection and classification pipelines for processing visual data. The NEOVUS architecture is inspired by the ventral (what) and dorsal (where) streams of the mammalian visual pathway and integrates retinal processing, object detection based on form and motion modeling, and object classification based on convolutional neural networks. The object recognition performance and energy use of the NEOVUS was evaluated by the Defense Advanced Research Projects Agency (DARPA) under the Neovision2 program using three urban area video datasets collected from a mix of stationary and moving platforms. These datasets are challenging and include a large number of objects of different types in cluttered scenes, with varying illumination and occlusion conditions. In a systematic evaluation of five different teams by DARPA on these datasets, the NEOVUS demonstrated the best performance with high object recognition accuracy and the lowest energy consumption. Its energy use was three orders of magnitude lower than two independent state of the art baseline computer vision systems. The dynamic power requirement for the complete system mapped to commercial off-the-shelf (COTS) hardware that includes a 5.6 Megapixel color camera processed by object detection and classification algorithms at 30 frames per second was measured at 21.7 Watts (W), for an effective energy consumption of 5.45 nanoJoules (nJ) per bit of incoming video. These unprecedented results show that the NEOVUS has the potential to revolutionize automated video object recognition toward enabling practical low-power and mobile video processing

  5. A neuromorphic system for video object recognition

    PubMed Central

    Khosla, Deepak; Chen, Yang; Kim, Kyungnam

    2014-01-01

    Automated video object recognition is a topic of emerging importance in both defense and civilian applications. This work describes an accurate and low-power neuromorphic architecture and system for real-time automated video object recognition. Our system, Neuormorphic Visual Understanding of Scenes (NEOVUS), is inspired by computational neuroscience models of feed-forward object detection and classification pipelines for processing visual data. The NEOVUS architecture is inspired by the ventral (what) and dorsal (where) streams of the mammalian visual pathway and integrates retinal processing, object detection based on form and motion modeling, and object classification based on convolutional neural networks. The object recognition performance and energy use of the NEOVUS was evaluated by the Defense Advanced Research Projects Agency (DARPA) under the Neovision2 program using three urban area video datasets collected from a mix of stationary and moving platforms. These datasets are challenging and include a large number of objects of different types in cluttered scenes, with varying illumination and occlusion conditions. In a systematic evaluation of five different teams by DARPA on these datasets, the NEOVUS demonstrated the best performance with high object recognition accuracy and the lowest energy consumption. Its energy use was three orders of magnitude lower than two independent state of the art baseline computer vision systems. The dynamic power requirement for the complete system mapped to commercial off-the-shelf (COTS) hardware that includes a 5.6 Megapixel color camera processed by object detection and classification algorithms at 30 frames per second was measured at 21.7 Watts (W), for an effective energy consumption of 5.45 nanoJoules (nJ) per bit of incoming video. These unprecedented results show that the NEOVUS has the potential to revolutionize automated video object recognition toward enabling practical low-power and mobile video processing

  6. Visual object recognition.

    PubMed

    Logothetis, N K; Sheinberg, D L

    1996-01-01

    Visual object recognition is of fundamental importance to most animals. The diversity of tasks that any biological recognition system must solve suggests that object recognition is not a single, general purpose process. In this review, we consider evidence from the fields of psychology, neuropsychology, and neurophysiology, all of which supports the idea that there are multiple systems for recognition. Data from normal adults, infants, animals, and brain damaged patients reveal a major distinction between the classification of objects at a basic category level and the identification of individual objects from a homogeneous object class. An additional distinction between object representations used for visual perception and those used for visually guided movements provides further support for a multiplicity of visual recognition systems. Recent evidence from psychophysical and neurophysiological studies indicates that one system may represent objects by combinations of multiple views, or aspects, and another may represent objects by structural primitives and their spatial interrelationships.

  7. Individual differences in involvement of the visual object recognition system during visual word recognition.

    PubMed

    Laszlo, Sarah; Sacchi, Elizabeth

    2015-01-01

    Individuals with dyslexia often evince reduced activation during reading in left hemisphere (LH) language regions. This can be observed along with increased activation in the right hemisphere (RH), especially in areas associated with object recognition - a pattern referred to as RH compensation. The mechanisms of RH compensation are relatively unclear. We hypothesize that RH compensation occurs when the RH object recognition system is called upon to supplement an underperforming LH visual word form recognition system. We tested this by collecting ERPs while participants with a range of reading abilities viewed words, objects, and word/object ambiguous items (e.g., "SMILE" shaped like a smile). Less experienced readers differentiate words, objects, and ambiguous items less strongly, especially over the RH. We suggest that this lack of differentiation may have negative consequences for dyslexic individuals demonstrating RH compensation.

  8. New neural-networks-based 3D object recognition system

    NASA Astrophysics Data System (ADS)

    Abolmaesumi, Purang; Jahed, M.

    1997-09-01

    Three-dimensional object recognition has always been one of the challenging fields in computer vision. In recent years, Ulman and Basri (1991) have proposed that this task can be done by using a database of 2-D views of the objects. The main problem in their proposed system is that the correspondent points should be known to interpolate the views. On the other hand, their system should have a supervisor to decide which class does the represented view belong to. In this paper, we propose a new momentum-Fourier descriptor that is invariant to scale, translation, and rotation. This descriptor provides the input feature vectors to our proposed system. By using the Dystal network, we show that the objects can be classified with over 95% precision. We have used this system to classify the objects like cube, cone, sphere, torus, and cylinder. Because of the nature of the Dystal network, this system reaches to its stable point by a single representation of the view to the system. This system can also classify the similar views to a single class (e.g., for the cube, the system generated 9 different classes for 50 different input views), which can be used to select an optimum database of training views. The system is also very flexible to the noise and deformed views.

  9. Automatic object recognition

    NASA Technical Reports Server (NTRS)

    Ranganath, H. S.; Mcingvale, Pat; Sage, Heinz

    1988-01-01

    Geometric and intensity features are very useful in object recognition. An intensity feature is a measure of contrast between object pixels and background pixels. Geometric features provide shape and size information. A model based approach is presented for computing geometric features. Knowledge about objects and imaging system is used to estimate orientation of objects with respect to the line of sight.

  10. Visual object recognition for mobile tourist information systems

    NASA Astrophysics Data System (ADS)

    Paletta, Lucas; Fritz, Gerald; Seifert, Christin; Luley, Patrick; Almer, Alexander

    2005-03-01

    We describe a mobile vision system that is capable of automated object identification using images captured from a PDA or a camera phone. We present a solution for the enabling technology of outdoors vision based object recognition that will extend state-of-the-art location and context aware services towards object based awareness in urban environments. In the proposed application scenario, tourist pedestrians are equipped with GPS, W-LAN and a camera attached to a PDA or a camera phone. They are interested whether their field of view contains tourist sights that would point to more detailed information. Multimedia type data about related history, the architecture, or other related cultural context of historic or artistic relevance might be explored by a mobile user who is intending to learn within the urban environment. Learning from ambient cues is in this way achieved by pointing the device towards the urban sight, capturing an image, and consequently getting information about the object on site and within the focus of attention, i.e., the users current field of view.

  11. Poka Yoke system based on image analysis and object recognition

    NASA Astrophysics Data System (ADS)

    Belu, N.; Ionescu, L. M.; Misztal, A.; Mazăre, A.

    2015-11-01

    Poka Yoke is a method of quality management which is related to prevent faults from arising during production processes. It deals with “fail-sating” or “mistake-proofing”. The Poka-yoke concept was generated and developed by Shigeo Shingo for the Toyota Production System. Poka Yoke is used in many fields, especially in monitoring production processes. In many cases, identifying faults in a production process involves a higher cost than necessary cost of disposal. Usually, poke yoke solutions are based on multiple sensors that identify some nonconformities. This means the presence of different equipment (mechanical, electronic) on production line. As a consequence, coupled with the fact that the method itself is an invasive, affecting the production process, would increase its price diagnostics. The bulky machines are the means by which a Poka Yoke system can be implemented become more sophisticated. In this paper we propose a solution for the Poka Yoke system based on image analysis and identification of faults. The solution consists of a module for image acquisition, mid-level processing and an object recognition module using associative memory (Hopfield network type). All are integrated into an embedded system with AD (Analog to Digital) converter and Zync 7000 (22 nm technology).

  12. A primitive-based 3D object recognition system

    NASA Technical Reports Server (NTRS)

    Dhawan, Atam P.

    1988-01-01

    An intermediate-level knowledge-based system for decomposing segmented data into three-dimensional primitives was developed to create an approximate three-dimensional description of the real world scene from a single two-dimensional perspective view. A knowledge-based approach was also developed for high-level primitive-based matching of three-dimensional objects. Both the intermediate-level decomposition and the high-level interpretation are based on the structural and relational matching; moreover, they are implemented in a frame-based environment.

  13. Object oriented image analysis based on multi-agent recognition system

    NASA Astrophysics Data System (ADS)

    Tabib Mahmoudi, Fatemeh; Samadzadegan, Farhad; Reinartz, Peter

    2013-04-01

    In this paper, the capabilities of multi-agent systems are used in order to solve object recognition difficulties in complex urban areas based on the characteristics of WorldView-2 satellite imagery and digital surface model (DSM). The proposed methodology has three main steps: pre-processing of dataset, object based image analysis and multi-agent object recognition. Classified regions obtained from object based image analysis are used as input datasets in the proposed multi-agent system in order to modify/improve results. In the first operational level of the proposed multi-agent system, various kinds of object recognition agents modify initial classified regions based on their spectral, textural and 3D structural knowledge. Then, in the second operational level, 2D structural knowledge and contextual relations are used by agents for reasoning and modification. Evaluation of the capabilities of the proposed object recognition methodology is performed on WorldView-2 imagery over Rio de Janeiro (Brazil) which has been collected in January 2010. According to the obtained results of the object based image analysis process, contextual relations and structural descriptors have high potential to modify general difficulties of object recognition. Using knowledge based reasoning and cooperative capabilities of agents in the proposed multi-agent system in this paper, most of the remaining difficulties are decreased and the accuracy of object based image analysis results is improved for about three percent.

  14. Neuropeptide S interacts with the basolateral amygdala noradrenergic system in facilitating object recognition memory consolidation.

    PubMed

    Han, Ren-Wen; Xu, Hong-Jiao; Zhang, Rui-San; Wang, Pei; Chang, Min; Peng, Ya-Li; Deng, Ke-Yu; Wang, Rui

    2014-01-01

    The noradrenergic activity in the basolateral amygdala (BLA) was reported to be involved in the regulation of object recognition memory. As the BLA expresses high density of receptors for Neuropeptide S (NPS), we investigated whether the BLA is involved in mediating NPS's effects on object recognition memory consolidation and whether such effects require noradrenergic activity. Intracerebroventricular infusion of NPS (1nmol) post training facilitated 24-h memory in a mouse novel object recognition task. The memory-enhancing effect of NPS could be blocked by the β-adrenoceptor antagonist propranolol. Furthermore, post-training intra-BLA infusions of NPS (0.5nmol/side) improved 24-h memory for objects, which was impaired by co-administration of propranolol (0.5μg/side). Taken together, these results indicate that NPS interacts with the BLA noradrenergic system in improving object recognition memory during consolidation.

  15. Toward a unified model of face and object recognition in the human visual system

    PubMed Central

    Wallis, Guy

    2013-01-01

    Our understanding of the mechanisms and neural substrates underlying visual recognition has made considerable progress over the past 30 years. During this period, accumulating evidence has led many scientists to conclude that objects and faces are recognised in fundamentally distinct ways, and in fundamentally distinct cortical areas. In the psychological literature, in particular, this dissociation has led to a palpable disconnect between theories of how we process and represent the two classes of object. This paper follows a trend in part of the recognition literature to try to reconcile what we know about these two forms of recognition by considering the effects of learning. Taking a widely accepted, self-organizing model of object recognition, this paper explains how such a system is affected by repeated exposure to specific stimulus classes. In so doing, it explains how many aspects of recognition generally regarded as unusual to faces (holistic processing, configural processing, sensitivity to inversion, the other-race effect, the prototype effect, etc.) are emergent properties of category-specific learning within such a system. Overall, the paper describes how a single model of recognition learning can and does produce the seemingly very different types of representation associated with faces and objects. PMID:23966963

  16. An Event-Based Neurobiological Recognition System with Orientation Detector for Objects in Multiple Orientations.

    PubMed

    Wang, Hanyu; Xu, Jiangtao; Gao, Zhiyuan; Lu, Chengye; Yao, Suying; Ma, Jianguo

    2016-01-01

    A new multiple orientation event-based neurobiological recognition system is proposed by integrating recognition and tracking function in this paper, which is used for asynchronous address-event representation (AER) image sensors. The characteristic of this system has been enriched to recognize the objects in multiple orientations with only training samples moving in a single orientation. The system extracts multi-scale and multi-orientation line features inspired by models of the primate visual cortex. An orientation detector based on modified Gaussian blob tracking algorithm is introduced for object tracking and orientation detection. The orientation detector and feature extraction block work in simultaneous mode, without any increase in categorization time. An addresses lookup table (addresses LUT) is also presented to adjust the feature maps by addresses mapping and reordering, and they are categorized in the trained spiking neural network. This recognition system is evaluated with the MNIST dataset which have played important roles in the development of computer vision, and the accuracy is increased owing to the use of both ON and OFF events. AER data acquired by a dynamic vision senses (DVS) are also tested on the system, such as moving digits, pokers, and vehicles. The experimental results show that the proposed system can realize event-based multi-orientation recognition. The work presented in this paper makes a number of contributions to the event-based vision processing system for multi-orientation object recognition. It develops a new tracking-recognition architecture to feedforward categorization system and an address reorder approach to classify multi-orientation objects using event-based data. It provides a new way to recognize multiple orientation objects with only samples in single orientation.

  17. An Event-Based Neurobiological Recognition System with Orientation Detector for Objects in Multiple Orientations

    PubMed Central

    Wang, Hanyu; Xu, Jiangtao; Gao, Zhiyuan; Lu, Chengye; Yao, Suying; Ma, Jianguo

    2016-01-01

    A new multiple orientation event-based neurobiological recognition system is proposed by integrating recognition and tracking function in this paper, which is used for asynchronous address-event representation (AER) image sensors. The characteristic of this system has been enriched to recognize the objects in multiple orientations with only training samples moving in a single orientation. The system extracts multi-scale and multi-orientation line features inspired by models of the primate visual cortex. An orientation detector based on modified Gaussian blob tracking algorithm is introduced for object tracking and orientation detection. The orientation detector and feature extraction block work in simultaneous mode, without any increase in categorization time. An addresses lookup table (addresses LUT) is also presented to adjust the feature maps by addresses mapping and reordering, and they are categorized in the trained spiking neural network. This recognition system is evaluated with the MNIST dataset which have played important roles in the development of computer vision, and the accuracy is increased owing to the use of both ON and OFF events. AER data acquired by a dynamic vision senses (DVS) are also tested on the system, such as moving digits, pokers, and vehicles. The experimental results show that the proposed system can realize event-based multi-orientation recognition. The work presented in this paper makes a number of contributions to the event-based vision processing system for multi-orientation object recognition. It develops a new tracking-recognition architecture to feedforward categorization system and an address reorder approach to classify multi-orientation objects using event-based data. It provides a new way to recognize multiple orientation objects with only samples in single orientation. PMID:27867346

  18. Performance of a neural-network-based 3-D object recognition system

    NASA Astrophysics Data System (ADS)

    Rak, Steven J.; Kolodzy, Paul J.

    1991-08-01

    Object recognition in laser radar sensor imagery is a challenging application of neural networks. The task involves recognition of objects at a variety of distances and aspects with significant levels of sensor noise. These variables are related to sensor parameters such as sensor signal strength and angular resolution, as well as object range and viewing aspect. The effect of these parameters on a fixed recognition system based on log-polar mapped features and an unsupervised neural network classifier are investigated. This work is an attempt to quantify the design parameters of a laser radar measurement system with respect to classifying and/or identifying objects by the shape of their silhouettes. Experiments with vehicle silhouettes rotated through 90 deg-of-view angle from broadside to head-on ('out-of-plane' rotation) have been used to quantify the performance of a log-polar map/neural-network based 3-D object recognition system. These experiments investigated several key issues such as category stability, category memory compression, image fidelity, and viewing aspect. Initial results indicate a compression from 720 possible categories (8 vehicles X 90 out-of-plane rotations) to a classifier memory with approximately 30 stable recognition categories. These results parallel the human experience of studying an object from several viewing angles yet recognizing it through a wide range of viewing angles. Results are presented illustrating category formation for an eight vehicle dataset as a function of several sensor parameters. These include: (1) sensor noise, as a function of carrier-to-noise ratio; (2) pixels on the vehicle, related to angular resolution and target range; and (3) viewing aspect, as related to sensor-to-platform depression angle. This work contributes to the formation of a three- dimensional object recognition system.

  19. 3-D Object Recognition Using Combined Overhead And Robot Eye-In-Hand Vision System

    NASA Astrophysics Data System (ADS)

    Luc, Ren C.; Lin, Min-Hsiung

    1987-10-01

    A new approach for recognizing 3-D objects using a combined overhead and eye-in-hand vision system is presented. A novel eye-in-hand vision system using a fiber-optic image array is described. The significance of this approach is the fast and accurate recognition of 3-D object information compared to traditional stereo image processing. For the recognition of 3-D objects, the over-head vision system will take 2-D top view image and the eye-in-hand vision system will take side view images orthogonal to the top view image plane. We have developed and demonstrated a unique approach to integrate this 2-D information into a 3-D representation based on a new approach called "3-D Volumetric Descrip-tion from 2-D Orthogonal Projections". The Unimate PUMA 560 and TRAPIX 5500 real-time image processor have been used to test the success of the entire system.

  20. Real-time optical multiple object recognition and tracking system and method

    NASA Technical Reports Server (NTRS)

    Chao, Tien-Hsin (Inventor); Liu, Hua Kuang (Inventor)

    1987-01-01

    The invention relates to an apparatus and associated methods for the optical recognition and tracking of multiple objects in real time. Multiple point spatial filters are employed that pre-define the objects to be recognized at run-time. The system takes the basic technology of a Vander Lugt filter and adds a hololens. The technique replaces time, space and cost-intensive digital techniques. In place of multiple objects, the system can also recognize multiple orientations of a single object. This later capability has potential for space applications where space and weight are at a premium.

  1. Real-time optical multiple object recognition and tracking system and method

    NASA Astrophysics Data System (ADS)

    Chao, Tien-Hsin; Liu, Hua Kuang

    1987-12-01

    The invention relates to an apparatus and associated methods for the optical recognition and tracking of multiple objects in real time. Multiple point spatial filters are employed that pre-define the objects to be recognized at run-time. The system takes the basic technology of a Vander Lugt filter and adds a hololens. The technique replaces time, space and cost-intensive digital techniques. In place of multiple objects, the system can also recognize multiple orientations of a single object. This later capability has potential for space applications where space and weight are at a premium.

  2. Object recognition using metric shape.

    PubMed

    Lee, Young-Lim; Lind, Mats; Bingham, Ned; Bingham, Geoffrey P

    2012-09-15

    Most previous studies of 3D shape perception have shown a general inability to visually perceive metric shape. In line with this, studies of object recognition have shown that only qualitative differences, not quantitative or metric ones can be used effectively for object recognition. Recently, Bingham and Lind (2008) found that large perspective changes (≥ 45°) allow perception of metric shape and Lee and Bingham (2010) found that this, in turn, allowed accurate feedforward reaches-to-grasp objects varying in metric shape. We now investigated whether this information would allow accurate and effective recognition of objects that vary in respect to metric shape. Both judgment accuracies (d') and reaction times confirmed that, with the availability of visual information in large perspective changes, recognition of objects using quantitative as compared to qualitative properties was equivalent in accuracy and speed of judgments. The ability to recognize objects based on their metric shape is, therefore, a function of the availability or unavailability of requisite visual information. These issues and results are discussed in the context of the Two Visual System hypothesis of Milner and Goodale (1995, 2006). 2012 Elsevier Ltd. All rights reserved

  3. A knowledge-based object recognition system for applications in the space station

    NASA Astrophysics Data System (ADS)

    Dhawan, Atam P.

    1988-02-01

    A knowledge-based three-dimensional (3D) object recognition system is being developed. The system uses primitive-based hierarchical relational and structural matching for the recognition of 3D objects in the two-dimensional (2D) image for interpretation of the 3D scene. At present, the pre-processing, low-level preliminary segmentation, rule-based segmentation, and the feature extraction are completed. The data structure of the primitive viewing knowledge-base (PVKB) is also completed. Algorithms and programs based on attribute-trees matching for decomposing the segmented data into valid primitives were developed. The frame-based structural and relational descriptions of some objects were created and stored in a knowledge-base. This knowledge-base of the frame-based descriptions were developed on the MICROVAX-AI microcomputer in LISP environment. The simulated 3D scene of simple non-overlapping objects as well as real camera data of images of 3D objects of low-complexity have been successfully interpreted.

  4. A knowledge-based object recognition system for applications in the space station

    NASA Technical Reports Server (NTRS)

    Dhawan, Atam P.

    1988-01-01

    A knowledge-based three-dimensional (3D) object recognition system is being developed. The system uses primitive-based hierarchical relational and structural matching for the recognition of 3D objects in the two-dimensional (2D) image for interpretation of the 3D scene. At present, the pre-processing, low-level preliminary segmentation, rule-based segmentation, and the feature extraction are completed. The data structure of the primitive viewing knowledge-base (PVKB) is also completed. Algorithms and programs based on attribute-trees matching for decomposing the segmented data into valid primitives were developed. The frame-based structural and relational descriptions of some objects were created and stored in a knowledge-base. This knowledge-base of the frame-based descriptions were developed on the MICROVAX-AI microcomputer in LISP environment. The simulated 3D scene of simple non-overlapping objects as well as real camera data of images of 3D objects of low-complexity have been successfully interpreted.

  5. An Intelligent Systems Approach to Automated Object Recognition: A Preliminary Study

    USGS Publications Warehouse

    Maddox, Brian G.; Swadley, Casey L.

    2002-01-01

    Attempts at fully automated object recognition systems have met with varying levels of success over the years. However, none of the systems have achieved high enough accuracy rates to be run unattended. One of the reasons for this may be that they are designed from the computer's point of view and rely mainly on image-processing methods. A better solution to this problem may be to make use of modern advances in computational intelligence and distributed processing to try to mimic how the human brain is thought to recognize objects. As humans combine cognitive processes with detection techniques, such a system would combine traditional image-processing techniques with computer-based intelligence to determine the identity of various objects in a scene.

  6. Real-time optical multiple object recognition and tracking system and method

    NASA Technical Reports Server (NTRS)

    Chao, Tien-Hsin (Inventor); Liu, Hua-Kuang (Inventor)

    1990-01-01

    System for optically recognizing and tracking a plurality of objects within a field of vision. Laser (46) produces a coherent beam (48). Beam splitter (24) splits the beam into object (26) and reference (28) beams. Beam expanders (50) and collimators (52) transform the beams (26, 28) into coherent collimated light beams (26', 28'). A two-dimensional SLM (54), disposed in the object beam (26'), modulates the object beam with optical information as a function of signals from a first camera (16) which develops X and Y signals reflecting the contents of its field of vision. A hololens (38), positioned in the object beam (26') subsequent to the modulator (54), focuses the object beam at a plurality of focal points (42). A planar transparency-forming film (32), disposed with the focal points on an exposable surface, forms a multiple position interference filter (62) upon exposure of the surface and development processing of the film (32). A reflector (53) directing the reference beam (28') onto the film (32), exposes the surface, with images focused by the hololens (38), to form interference patterns on the surface. There is apparatus (16', 64) for sensing and indicating light passage through respective ones of the positions of the filter (62), whereby recognition of objects corresponding to respective ones of the positions of the filter (62) is affected. For tracking, apparatus (64) focuses light passing through the filter (62) onto a matrix of CCD's in a second camera (16') to form a two-dimensional display of the recognized objects.

  7. Geometric filtration of classification-based object detectors in realtime road scene recognition systems

    NASA Astrophysics Data System (ADS)

    Prun, Viktor; Bocharov, Dmitry; Koptelov, Ivan; Sholomov, Dmitry; Postnikov, Vassily

    2015-12-01

    We study the issue of performance improvement of classification-based object detectors by including certain geometric-oriented filters. Configurations of the observed 3D scene may be used as a priori or a posteriori information for object filtration. A priori information is used to select only those object parameters (size and position on image plane) that are in accordance with the scene, restricting implausible combinations of parameters. On the other hand the detection robustness can be enhanced by rejecting detection results using a posteriori information about 3D scene. For example, relative location of detected objects can be used as criteria for filtration. We have included proposed filters in object detection modules of two different industrial vision-based recognition systems and compared the resulting detection quality before detectors improving and after. Filtering with a priori information leads to significant decrease of detector's running time per frame and increase of number of correctly detected objects. Including filter based on a posteriori information leads to decrease of object detection false positive rate.

  8. An optimal sensing strategy of a proximity sensor system for recognition and localization of polyhedral objects

    NASA Technical Reports Server (NTRS)

    Lee, Sukhan; Hahn, Hern S.

    1990-01-01

    An algorithm is presented for the recognition and localization of thre-dimensional polyhedral objects based on an optical proximity sensor system capable of measuring the depth and orientation of a local area of an object surface. Emphasis is given to the determination of an optimal sensor trajectory or an optimal probing, for efficient discrimination among all the possible interpretations. The determination of an optimal sensor trajectory for the next probing consists of the selection of optimal beam orientations based on the surface normal vector distribution of the multiple interpretation image (MII) and the selection of an optimal probing plane by projecting the MII onto the projection plane perpendicular to a selected beam orientation and deriving the optimal path on the projection plane. The selection of optimal beam orientation and probing plane is based on the measure of discrimination power of a cluster of surfaces of an MII. Simulation results are shown.

  9. Coordinate Transformations in Object Recognition

    ERIC Educational Resources Information Center

    Graf, Markus

    2006-01-01

    A basic problem of visual perception is how human beings recognize objects after spatial transformations. Three central classes of findings have to be accounted for: (a) Recognition performance varies systematically with orientation, size, and position; (b) recognition latencies are sequentially additive, suggesting analogue transformation…

  10. Object recognition memory in zebrafish.

    PubMed

    May, Zacnicte; Morrill, Adam; Holcombe, Adam; Johnston, Travis; Gallup, Joshua; Fouad, Karim; Schalomon, Melike; Hamilton, Trevor James

    2016-01-01

    The novel object recognition, or novel-object preference (NOP) test is employed to assess recognition memory in a variety of organisms. The subject is exposed to two identical objects, then after a delay, it is placed back in the original environment containing one of the original objects and a novel object. If the subject spends more time exploring one object, this can be interpreted as memory retention. To date, this test has not been fully explored in zebrafish (Danio rerio). Zebrafish possess recognition memory for simple 2- and 3-dimensional geometrical shapes, yet it is unknown if this translates to complex 3-dimensional objects. In this study we evaluated recognition memory in zebrafish using complex objects of different sizes. Contrary to rodents, zebrafish preferentially explored familiar over novel objects. Familiarity preference disappeared after delays of 5 mins. Leopard danios, another strain of D. rerio, also preferred the familiar object after a 1 min delay. Object preference could be re-established in zebra danios by administration of nicotine tartrate salt (50mg/L) prior to stimuli presentation, suggesting a memory-enhancing effect of nicotine. Additionally, exploration biases were present only when the objects were of intermediate size (2 × 5 cm). Our results demonstrate zebra and leopard danios have recognition memory, and that low nicotine doses can improve this memory type in zebra danios. However, exploration biases, from which memory is inferred, depend on object size. These findings suggest zebrafish ecology might influence object preference, as zebrafish neophobia could reflect natural anti-predatory behaviour. Copyright © 2015 Elsevier B.V. All rights reserved.

  11. An introduction to object recognition.

    PubMed

    Liter, J C; Bülthoff, H H

    1998-01-01

    In this report we present a general introduction to object recognition. We begin with brief discussions of the terminology used in the object recognition literature and the psychophysical tasks that are used to investigate object recognition. We then discuss models of shape representation. We dispense with the idea that shape representations are like the 3-D models used in computer aided design and explore instead models of shape representation that are based on future descriptions. As these descriptions encode only the features that are visible from a particular viewpoint, they are generally viewpoint-specific. We discuss various means of achieving viewpoint-invariant recognition using such descriptions, including reliance on diagnostic features visible from a wide range of viewpoints, storage of multiple descriptions for each object, and the use of transformation mechanisms. Finally, we discuss how differences in viewpoint dependence that are often observed for within-category and between-category recognition tasks could be due to differences in the types of features that are naturally available to distinguish among different objects in these tasks.

  12. Recurrent Processing during Object Recognition

    PubMed Central

    O’Reilly, Randall C.; Wyatte, Dean; Herd, Seth; Mingus, Brian; Jilk, David J.

    2013-01-01

    How does the brain learn to recognize objects visually, and perform this difficult feat robustly in the face of many sources of ambiguity and variability? We present a computational model based on the biology of the relevant visual pathways that learns to reliably recognize 100 different object categories in the face of naturally occurring variability in location, rotation, size, and lighting. The model exhibits robustness to highly ambiguous, partially occluded inputs. Both the unified, biologically plausible learning mechanism and the robustness to occlusion derive from the role that recurrent connectivity and recurrent processing mechanisms play in the model. Furthermore, this interaction of recurrent connectivity and learning predicts that high-level visual representations should be shaped by error signals from nearby, associated brain areas over the course of visual learning. Consistent with this prediction, we show how semantic knowledge about object categories changes the nature of their learned visual representations, as well as how this representational shift supports the mapping between perceptual and conceptual knowledge. Altogether, these findings support the potential importance of ongoing recurrent processing throughout the brain’s visual system and suggest ways in which object recognition can be understood in terms of interactions within and between processes over time. PMID:23554596

  13. Acoustic signature recognition technique for Human-Object Interactions (HOI) in persistent surveillance systems

    NASA Astrophysics Data System (ADS)

    Alkilani, Amjad; Shirkhodaie, Amir

    2013-05-01

    Handling, manipulation, and placement of objects, hereon called Human-Object Interaction (HOI), in the environment generate sounds. Such sounds are readily identifiable by the human hearing. However, in the presence of background environment noises, recognition of minute HOI sounds is challenging, though vital for improvement of multi-modality sensor data fusion in Persistent Surveillance Systems (PSS). Identification of HOI sound signatures can be used as precursors to detection of pertinent threats that otherwise other sensor modalities may miss to detect. In this paper, we present a robust method for detection and classification of HOI events via clustering of extracted features from training of HOI acoustic sound waves. In this approach, salient sound events are preliminary identified and segmented from background via a sound energy tracking method. Upon this segmentation, frequency spectral pattern of each sound event is modeled and its features are extracted to form a feature vector for training. To reduce dimensionality of training feature space, a Principal Component Analysis (PCA) technique is employed to expedite fast classification of test feature vectors, a kd-tree and Random Forest classifiers are trained for rapid classification of training sound waves. Each classifiers employs different similarity distance matching technique for classification. Performance evaluations of classifiers are compared for classification of a batch of training HOI acoustic signatures. Furthermore, to facilitate semantic annotation of acoustic sound events, a scheme based on Transducer Mockup Language (TML) is proposed. The results demonstrate the proposed approach is both reliable and effective, and can be extended to future PSS applications.

  14. Real-time unconstrained object recognition: a processing pipeline based on the mammalian visual system.

    PubMed

    Aguilar, Mario; Peot, Mark A; Zhou, Jiangying; Simons, Stephen; Liao, Yuwei; Metwalli, Nader; Anderson, Mark B

    2012-03-01

    The mammalian visual system is still the gold standard for recognition accuracy, flexibility, efficiency, and speed. Ongoing advances in our understanding of function and mechanisms in the visual system can now be leveraged to pursue the design of computer vision architectures that will revolutionize the state of the art in computer vision.

  15. A Model-Based System For Object Recognition In Aerial Scenes

    NASA Astrophysics Data System (ADS)

    Cullen, M. F.; Hord, R. M.; Miller, S. F.

    1987-03-01

    Preliminary results of a system that uses model descriptions of objects to predict and match features derived from aerial images are presented. The system is organized into several phases: 1) processing of image scenes to obtain image primitives, 2) goal-oriented sorting of primitives into classes of related features, 3) prediction of the location of object model features in the image, and 4) matching image features to the model predicted features. The matching approach is centered upon a compatibility figure of merit between a set of image features and model features chosen to direct the search. The search process utilizes an iterative hypothesis generation and verication cycle. A "search matrix" is con-structed from image features and model features according to a first approximation of compatibility based upon orientation. Currently, linear features are used as primitives. Input to the matching algorithm is in the form of line segments extracted from an image scene via edge operatiors and a Hough transform technique for grouping. Additional processing is utilized to derive closed boundaries and complete edge descriptions. Line segments are then sorted into specific classes such that, on a higher level, a priori knowledge about a particular scene can be used to control the priority of line segments in the search process. Additional knowledge about the object model under consideration is utilized to construct the search matrix with the classes of line segments most likely containing the model description. It is shown that these techniques result in a, reduction in the size of the object recognition search space and hence in the time to locate the object in the image. The current system is implemented on a Symbolics LispTM machine. While experimentation continues, we have rewritten and tested the search process and several image processing functions for parallel implementation on a Connection Machine TM computer. It is shown that several orders of magnitude faster

  16. Paradoxical facilitation of object recognition memory after infusion of scopolamine into perirhinal cortex: implications for cholinergic system function.

    PubMed

    Winters, Boyer D; Saksida, Lisa M; Bussey, Timothy J

    2006-09-13

    The cholinergic system has long been implicated in learning and memory, yet its specific function remains unclear. In the present study, we investigated the role of cortical acetylcholine in a rodent model of declarative memory by infusing the cholinergic muscarinic receptor antagonist scopolamine into the rat perirhinal cortex during different stages (encoding, storage/consolidation, and retrieval) of the spontaneous object recognition task. Presample infusions of scopolamine significantly impaired object recognition compared with performance of the same group of rats on saline trials; this result is consistent with previous reports supporting a role for perirhinal acetylcholine in object information acquisition. Scopolamine infusions directly before the retrieval stage had no discernible effect on object recognition. However, postsample infusions of scopolamine with sample-to-infusion delays of up to 20 h significantly facilitated performance relative to postsample saline infusion trials. Additional analysis suggested that the infusion episode could cause retroactive or proactive interference with the sample object trace and that scopolamine blocked the acquisition of this interfering information, thereby facilitating recognition memory. This is, to our knowledge, the first example of improved recognition memory after administration of scopolamine. The overall pattern of results is inconsistent with a direct role for cortical acetylcholine in declarative memory consolidation or retrieval. Rather, the cholinergic input to the perirhinal cortex may facilitate acquisition by enhancing the cortical processing of incoming stimulus information.

  17. Recognition of movement object collision

    NASA Astrophysics Data System (ADS)

    Chang, Hsiao Tsu; Sun, Geng-tian; Zhang, Yan

    1991-03-01

    The paper explores the collision recognition of two objects in both crisscross and revolution motions A mathematical model has been established based on the continuation theory. The objects of any shape may be regarded as being built of many 3siniplexes or their convex hulls. Therefore the collision problem of two object in motion can be reduced to the collision of two corresponding 3siinplexes on two respective objects accordingly. Thus an optimized algorithm is developed for collision avoidance which is suitable for computer control and eliminating the need for vision aid. With this algorithm computation time has been reduced significantly. This algorithm is applicable to the path planning of mobile robots And also is applicable to collision avoidance of the anthropomorphic arms grasping two complicated shaped objects. The algorithm is realized using LISP language on a VAX8350 minicomputer.

  18. Interactive object recognition assistance: an approach to recognition starting from target objects

    NASA Astrophysics Data System (ADS)

    Geisler, Juergen; Littfass, Michael

    1999-07-01

    Recognition of target objects in remotely sensed imagery required detailed knowledge about the target object domain as well as about mapping properties of the sensing system. The art of object recognition is to combine both worlds appropriately and to provide models of target appearance with respect to sensor characteristics. Common approaches to support interactive object recognition are either driven from the sensor point of view and address the problem of displaying images in a manner adequate to the sensing system. Or they focus on target objects and provide exhaustive encyclopedic information about this domain. Our paper discusses an approach to assist interactive object recognition based on knowledge about target objects and taking into account the significance of object features with respect to characteristics of the sensed imagery, e.g. spatial and spectral resolution. An `interactive recognition assistant' takes the image analyst through the interpretation process by indicating step-by-step the respectively most significant features of objects in an actual set of candidates. The significance of object features is expressed by pregenerated trees of significance, and by the dynamic computation of decision relevance for every feature at each step of the recognition process. In the context of this approach we discuss the question of modeling and storing the multisensorial/multispectral appearances of target objects and object classes as well as the problem of an adequate dynamic human-machine-interface that takes into account various mental models of human image interpretation.

  19. Visual object recognition and tracking

    NASA Technical Reports Server (NTRS)

    Chang, Chu-Yin (Inventor); English, James D. (Inventor); Tardella, Neil M. (Inventor)

    2010-01-01

    This invention describes a method for identifying and tracking an object from two-dimensional data pictorially representing said object by an object-tracking system through processing said two-dimensional data using at least one tracker-identifier belonging to the object-tracking system for providing an output signal containing: a) a type of the object, and/or b) a position or an orientation of the object in three-dimensions, and/or c) an articulation or a shape change of said object in said three dimensions.

  20. Systemic and intra-rhinal-cortical 17-β estradiol administration modulate object-recognition memory in ovariectomized female rats.

    PubMed

    Gervais, Nicole J; Jacob, Sofia; Brake, Wayne G; Mumby, Dave G

    2013-09-01

    Previous studies using the novel-object-preference (NOP) test suggest that estrogen (E) replacement in ovariectomized rodents can lead to enhanced novelty preference. The present study aimed to determine: 1) whether the effect of E on NOP performance is the result of enhanced preference for novelty, per se, or facilitated object-recognition memory, and 2) whether E affects NOP performance through actions it has within the perirhinal cortex/entorhinal cortex region (PRh/EC). Ovariectomized rats received either systemic chronic low 17-β estradiol (E2; ~20 pg/ml serum) replacement alone or in combination with systemic acute high administration of estradiol benzoate (EB; 10 μg), or in combination with intracranial infusions of E2 (244.8 pg/μl) or vehicle into the PRh/EC. For one of the intracranial experiments, E2 was infused either immediately before, immediately after, or 2 h following the familiarization (i.e., learning) phase of the NOP test. In light of recent evidence that raises questions about the internal validity of the NOP test as a method of indexing object-recognition memory, we also tested rats on a delayed nonmatch-to-sample (DNMS) task of object recognition following systemic and intra-PRh/EC infusions of E2. Both systemic acute and intra-PRh/EC infusions of E enhanced novelty preference, but only when administered either before or immediately following familiarization. In contrast, high E (both systemic acute and intra-PRh/EC) impaired performance on the DNMS task. The findings suggest that while E2 in the PRh/EC can enhance novelty preference, this effect is probably not due to an improvement in object-recognition abilities.

  1. HFirst: A Temporal Approach to Object Recognition.

    PubMed

    Orchard, Garrick; Meyer, Cedric; Etienne-Cummings, Ralph; Posch, Christoph; Thakor, Nitish; Benosman, Ryad

    2015-10-01

    This paper introduces a spiking hierarchical model for object recognition which utilizes the precise timing information inherently present in the output of biologically inspired asynchronous address event representation (AER) vision sensors. The asynchronous nature of these systems frees computation and communication from the rigid predetermined timing enforced by system clocks in conventional systems. Freedom from rigid timing constraints opens the possibility of using true timing to our advantage in computation. We show not only how timing can be used in object recognition, but also how it can in fact simplify computation. Specifically, we rely on a simple temporal-winner-take-all rather than more computationally intensive synchronous operations typically used in biologically inspired neural networks for object recognition. This approach to visual computation represents a major paradigm shift from conventional clocked systems and can find application in other sensory modalities and computational tasks. We showcase effectiveness of the approach by achieving the highest reported accuracy to date (97.5% ± 3.5%) for a previously published four class card pip recognition task and an accuracy of 84.9% ± 1.9% for a new more difficult 36 class character recognition task.

  2. A fast 3-D object recognition algorithm for the vision system of a special-purpose dexterous manipulator

    NASA Technical Reports Server (NTRS)

    Hung, Stephen H. Y.

    1989-01-01

    A fast 3-D object recognition algorithm that can be used as a quick-look subsystem to the vision system for the Special-Purpose Dexterous Manipulator (SPDM) is described. Global features that can be easily computed from range data are used to characterize the images of a viewer-centered model of an object. This algorithm will speed up the processing by eliminating the low level processing whenever possible. It may identify the object, reject a set of bad data in the early stage, or create a better environment for a more powerful algorithm to carry the work further.

  3. Disruptive camouflage impairs object recognition

    PubMed Central

    Webster, Richard J.; Hassall, Christopher; Herdman, Chris M.; Godin, Jean-Guy J.; Sherratt, Thomas N.

    2013-01-01

    Whether hiding from predators, or avoiding battlefield casualties, camouflage is widely employed to prevent detection. Disruptive coloration is a seemingly well-known camouflage mechanism proposed to function by breaking up an object's salient features (for example their characteristic outline), rendering objects more difficult to recognize. However, while a wide range of animals are thought to evade detection using disruptive patterns, there is no direct experimental evidence that disruptive coloration impairs recognition. Using humans searching for computer-generated moth targets, we demonstrate that the number of edge-intersecting patches on a target reduces the likelihood of it being detected, even at the expense of reduced background matching. Crucially, eye-tracking data show that targets with more edge-intersecting patches were looked at for longer periods prior to attack, and passed-over more frequently during search tasks. We therefore show directly that edge patches enhance survivorship by impairing recognition, confirming that disruptive coloration is a distinct camouflage strategy, not simply an artefact of background matching. PMID:24152693

  4. Probabilistic view clustering in object recognition

    NASA Astrophysics Data System (ADS)

    Camps, Octavia I.; Christoffel, Douglas W.; Pathak, Anjali

    1992-11-01

    To recognize objects and to determine their poses in a scene we need to find correspondences between the features extracted from the image and those of the object models. Models are commonly represented by describing a few characteristic views of the object representing groups of views with similar properties. Most feature-based matching schemes assume that all the features that are potentially visible in a view will appear with equal probability, and the resulting matching algorithms have to allow for 'errors' without really understanding what they mean. PREMIO is an object recognition system that uses CAD models of 3D objects and knowledge of surface reflectance properties, light sources, sensor characteristics, and feature detector algorithms to estimate the probability of the features being detectable and correctly matched. The purpose of this paper is to describe the predictions generated by PREMIO, how they are combined into a single probabilistic model, and illustrative examples showing its use in object recognition.

  5. Statistical Model For Pseudo-Moving Objects Recognition In Video Surveillance Systems

    NASA Astrophysics Data System (ADS)

    Vishnyakov, B.; Egorov, A.; Sidyakin, S.; Malin, I.; Vizilter, Y.

    2014-08-01

    This paper considers a statistical approach to define pseudo-moving (false) objects in video surveillance systems by constructing systems of hypothesis with the criteria based on statistical behavioral particularities. The obtained results are integrated in two ways: using the Bayes' theorem or the logistic regression. FAR-FRR curves are plotted for each system of hypothesis and also for the decision rule. The results of the proposed methods are obtained on test video databases.

  6. Object recognition by artificial cortical maps.

    PubMed

    Plebe, Alessio; Domenella, Rosaria Grazia

    2007-09-01

    Object recognition is one of the most important functions of the human visual system, yet one of the least understood, this despite the fact that vision is certainly the most studied function of the brain. We understand relatively well how several processes in the cortical visual areas that support recognition capabilities take place, such as orientation discrimination and color constancy. This paper proposes a model of the development of object recognition capability, based on two main theoretical principles. The first is that recognition does not imply any sort of geometrical reconstruction, it is instead fully driven by the two dimensional view captured by the retina. The second assumption is that all the processing functions involved in recognition are not genetically determined or hardwired in neural circuits, but are the result of interactions between epigenetic influences and basic neural plasticity mechanisms. The model is organized in modules roughly related to the main visual biological areas, and is implemented mainly using the LISSOM architecture, a recent neural self-organizing map model that simulates the effects of intercortical lateral connections. This paper shows how recognition capabilities, similar to those found in brain ventral visual areas, can develop spontaneously by exposure to natural images in an artificial cortical model.

  7. The uncrowded window of object recognition

    PubMed Central

    Pelli, Denis G; Tillman, Katharine A

    2009-01-01

    It is now emerging that vision is usually limited by object spacing rather than size. The visual system recognizes an object by detecting and then combining its features. ‘Crowding’ occurs when objects are too close together and features from several objects are combined into a jumbled percept. Here, we review the explosion of studies on crowding—in grating discrimination, letter and face recognition, visual search, selective attention, and reading—and find a universal principle, the Bouma law. The critical spacing required to prevent crowding is equal for all objects, although the effect is weaker between dissimilar objects. Furthermore, critical spacing at the cortex is independent of object position, and critical spacing at the visual field is proportional to object distance from fixation. The region where object spacing exceeds critical spacing is the ‘uncrowded window’. Observers cannot recognize objects outside of this window and its size limits the speed of reading and search. PMID:18828191

  8. Invariant object recognition based on extended fragments.

    PubMed

    Bart, Evgeniy; Hegdé, Jay

    2012-01-01

    Visual appearance of natural objects is profoundly affected by viewing conditions such as viewpoint and illumination. Human subjects can nevertheless compensate well for variations in these viewing conditions. The strategies that the visual system uses to accomplish this are largely unclear. Previous computational studies have suggested that in principle, certain types of object fragments (rather than whole objects) can be used for invariant recognition. However, whether the human visual system is actually capable of using this strategy remains unknown. Here, we show that human observers can achieve illumination invariance by using object fragments that carry the relevant information. To determine this, we have used novel, but naturalistic, 3-D visual objects called "digital embryos." Using novel instances of whole embryos, not fragments, we trained subjects to recognize individual embryos across illuminations. We then tested the illumination-invariant object recognition performance of subjects using fragments. We found that the performance was strongly correlated with the mutual information (MI) of the fragments, provided that MI value took variations in illumination into consideration. This correlation was not attributable to any systematic differences in task difficulty between different fragments. These results reveal two important principles of invariant object recognition. First, the subjects can achieve invariance at least in part by compensating for the changes in the appearance of small local features, rather than of whole objects. Second, the subjects do not always rely on generic or pre-existing invariance of features (i.e., features whose appearance remains largely unchanged by variations in illumination), and are capable of using learning to compensate for appearance changes when necessary. These psychophysical results closely fit the predictions of earlier computational studies of fragment-based invariant object recognition.

  9. Relations among Early Object Recognition Skills: Objects and Letters

    ERIC Educational Resources Information Center

    Augustine, Elaine; Jones, Susan S.; Smith, Linda B.; Longfield, Erica

    2015-01-01

    Human visual object recognition is multifaceted and comprised of several domains of expertise. Developmental relations between young children's letter recognition and their 3-dimensional object recognition abilities are implicated on several grounds but have received little research attention. Here, we ask how preschoolers' success in recognizing…

  10. Relations among Early Object Recognition Skills: Objects and Letters

    ERIC Educational Resources Information Center

    Augustine, Elaine; Jones, Susan S.; Smith, Linda B.; Longfield, Erica

    2015-01-01

    Human visual object recognition is multifaceted and comprised of several domains of expertise. Developmental relations between young children's letter recognition and their 3-dimensional object recognition abilities are implicated on several grounds but have received little research attention. Here, we ask how preschoolers' success in recognizing…

  11. REKRIATE: A Knowledge Representation System for Object Recognition and Scene Interpretation

    NASA Astrophysics Data System (ADS)

    Meystel, Alexander M.; Bhasin, Sanjay; Chen, X.

    1990-02-01

    What humans actually observe and how they comprehend this information is complex due to Gestalt processes and interaction of context in predicting the course of thinking and enforcing one idea while repressing another. How we extract the knowledge from the scene, what we get from the scene indeed and what we bring from our mechanisms of perception are areas separated by a thin, ill-defined line. The purpose of this paper is to present a system for Representing Knowledge and Recognizing and Interpreting Attention Trailed Entities dubbed as REKRIATE. It will be used as a tool for discovering the underlying principles involved in knowledge representation required for conceptual learning. REKRIATE has some inherited knowledge and is given a vocabulary which is used to form rules for identification of the object. It has various modalities of sensing and has the ability to measure the distance between the objects in the image as well as the similarity between different images of presumably the same object. All sensations received from matrix of different sensors put into an adequate form. The methodology proposed is applicable to not only the pictorial or visual world representation, but to any sensing modality. It is based upon the two premises: a) inseparability of all domains of the world representation including linguistic, as well as those formed by various sensor modalities. and b) representativity of the object at several levels of resolution simultaneously.

  12. Automatic recognition of partially occluded objects

    NASA Astrophysics Data System (ADS)

    Sadjadi, Firooz A.

    1992-09-01

    Machine recognition of partially occluded objects is essential for any realistic automatic object recognition (AOR) system. This important problem however, has been mostly ignored by the researchers and developers of AOR systems. Due to this lack of attention very little work is done even in the formulation of the problem and much less for its solution. In this paper I attempt to analyze the occlusion problem, define its various categories, and to present an approach for its solution in some of these categories. I also present some of the empirical results of the implementation of the approach on real imagery. These results have been very encouraging so far. However, more work is definitely needed to be done for the resolution of this problem.

  13. Three-Dimensional Object Recognition and Registration for Robotic Grasping Systems Using a Modified Viewpoint Feature Histogram.

    PubMed

    Chen, Chin-Sheng; Chen, Po-Chun; Hsu, Chih-Ming

    2016-11-23

    This paper presents a novel 3D feature descriptor for object recognition and to identify poses when there are six-degrees-of-freedom for mobile manipulation and grasping applications. Firstly, a Microsoft Kinect sensor is used to capture 3D point cloud data. A viewpoint feature histogram (VFH) descriptor for the 3D point cloud data then encodes the geometry and viewpoint, so an object can be simultaneously recognized and registered in a stable pose and the information is stored in a database. The VFH is robust to a large degree of surface noise and missing depth information so it is reliable for stereo data. However, the pose estimation for an object fails when the object is placed symmetrically to the viewpoint. To overcome this problem, this study proposes a modified viewpoint feature histogram (MVFH) descriptor that consists of two parts: a surface shape component that comprises an extended fast point feature histogram and an extended viewpoint direction component. The MVFH descriptor characterizes an object's pose and enhances the system's ability to identify objects with mirrored poses. Finally, the refined pose is further estimated using an iterative closest point when the object has been recognized and the pose roughly estimated by the MVFH descriptor and it has been registered on a database. The estimation results demonstrate that the MVFH feature descriptor allows more accurate pose estimation. The experiments also show that the proposed method can be applied in vision-guided robotic grasping systems.

  14. Exploiting core knowledge for visual object recognition.

    PubMed

    Schurgin, Mark W; Flombaum, Jonathan I

    2017-03-01

    Humans recognize thousands of objects, and with relative tolerance to variable retinal inputs. The acquisition of this ability is not fully understood, and it remains an area in which artificial systems have yet to surpass people. We sought to investigate the memory process that supports object recognition. Specifically, we investigated the association of inputs that co-occur over short periods of time. We tested the hypothesis that human perception exploits expectations about object kinematics to limit the scope of association to inputs that are likely to have the same token as a source. In several experiments we exposed participants to images of objects, and we then tested recognition sensitivity. Using motion, we manipulated whether successive encounters with an image took place through kinematics that implied the same or a different token as the source of those encounters. Images were injected with noise, or shown at varying orientations, and we included 2 manipulations of motion kinematics. Across all experiments, memory performance was better for images that had been previously encountered with kinematics that implied a single token. A model-based analysis similarly showed greater memory strength when images were shown via kinematics that implied a single token. These results suggest that constraints from physics are built into the mechanisms that support memory about objects. Such constraints-often characterized as 'Core Knowledge'-are known to support perception and cognition broadly, even in young infants. But they have never been considered as a mechanism for memory with respect to recognition. (PsycINFO Database Record

  15. Infant Visual Attention and Object Recognition

    PubMed Central

    Reynolds, Greg D.

    2015-01-01

    This paper explores the role visual attention plays in the recognition of objects in infancy. Research and theory on the development of infant attention and recognition memory are reviewed in three major sections. The first section reviews some of the major findings and theory emerging from a rich tradition of behavioral research utilizing preferential looking tasks to examine visual attention and recognition memory in infancy. The second section examines research utilizing neural measures of attention and object recognition in infancy as well as research on brain-behavior relations in the early development of attention and recognition memory. The third section addresses potential areas of the brain involved in infant object recognition and visual attention. An integrated synthesis of some of the existing models of the development of visual attention is presented which may account for the observed changes in behavioral and neural measures of visual attention and object recognition that occur across infancy. PMID:25596333

  16. Infant visual attention and object recognition.

    PubMed

    Reynolds, Greg D

    2015-05-15

    This paper explores the role visual attention plays in the recognition of objects in infancy. Research and theory on the development of infant attention and recognition memory are reviewed in three major sections. The first section reviews some of the major findings and theory emerging from a rich tradition of behavioral research utilizing preferential looking tasks to examine visual attention and recognition memory in infancy. The second section examines research utilizing neural measures of attention and object recognition in infancy as well as research on brain-behavior relations in the early development of attention and recognition memory. The third section addresses potential areas of the brain involved in infant object recognition and visual attention. An integrated synthesis of some of the existing models of the development of visual attention is presented which may account for the observed changes in behavioral and neural measures of visual attention and object recognition that occur across infancy.

  17. Relations among early object recognition skills: Objects and letters.

    PubMed

    Augustine, Elaine; Jones, Susan S; Smith, Linda B; Longfield, Erica

    2015-04-01

    Human visual object recognition is multifaceted, with several domains of expertise. Developmental relations between young children's letter recognition and their 3-dimensional object recognition abilities are implicated on several grounds but have received little research attention. Here, we ask how preschoolers' success in recognizing letters relates to their ability to recognize 3-dimensional objects from sparse shape information alone. A relation is predicted because perception of the spatial relations is critical in both domains. Seventy-three 2 ½- to 4-year-old children completed a Letter Recognition task, measuring the ability to identify a named letter among 3 letters with similar shapes, and a "Shape Caricature Recognition" task, measuring recognition of familiar objects from sparse, abstract information about their part shapes and the spatial relations among those parts. Children also completed a control "Shape Bias" task, in which success depends on recognition of overall object shape but not of relational structure. Children's success in letter recognition was positively related to their shape caricature recognition scores, but not to their shape bias scores. The results suggest that letter recognition builds upon developing skills in attending to and representing the relational structure of object shape, and that these skills are common to both 2-dimensional and 3-dimensional object perception.

  18. From brain synapses to systems for learning and memory: Object recognition, spatial navigation, timed conditioning, and movement control.

    PubMed

    Grossberg, Stephen

    2015-09-24

    This article provides an overview of neural models of synaptic learning and memory whose expression in adaptive behavior depends critically on the circuits and systems in which the synapses are embedded. It reviews Adaptive Resonance Theory, or ART, models that use excitatory matching and match-based learning to achieve fast category learning and whose learned memories are dynamically stabilized by top-down expectations, attentional focusing, and memory search. ART clarifies mechanistic relationships between consciousness, learning, expectation, attention, resonance, and synchrony. ART models are embedded in ARTSCAN architectures that unify processes of invariant object category learning, recognition, spatial and object attention, predictive remapping, and eye movement search, and that clarify how conscious object vision and recognition may fail during perceptual crowding and parietal neglect. The generality of learned categories depends upon a vigilance process that is regulated by acetylcholine via the nucleus basalis. Vigilance can get stuck at too high or too low values, thereby causing learning problems in autism and medial temporal amnesia. Similar synaptic learning laws support qualitatively different behaviors: Invariant object category learning in the inferotemporal cortex; learning of grid cells and place cells in the entorhinal and hippocampal cortices during spatial navigation; and learning of time cells in the entorhinal-hippocampal system during adaptively timed conditioning, including trace conditioning. Spatial and temporal processes through the medial and lateral entorhinal-hippocampal system seem to be carried out with homologous circuit designs. Variations of a shared laminar neocortical circuit design have modeled 3D vision, speech perception, and cognitive working memory and learning. A complementary kind of inhibitory matching and mismatch learning controls movement. This article is part of a Special Issue entitled SI: Brain and Memory

  19. Three-Dimensional Object Recognition and Registration for Robotic Grasping Systems Using a Modified Viewpoint Feature Histogram

    PubMed Central

    Chen, Chin-Sheng; Chen, Po-Chun; Hsu, Chih-Ming

    2016-01-01

    This paper presents a novel 3D feature descriptor for object recognition and to identify poses when there are six-degrees-of-freedom for mobile manipulation and grasping applications. Firstly, a Microsoft Kinect sensor is used to capture 3D point cloud data. A viewpoint feature histogram (VFH) descriptor for the 3D point cloud data then encodes the geometry and viewpoint, so an object can be simultaneously recognized and registered in a stable pose and the information is stored in a database. The VFH is robust to a large degree of surface noise and missing depth information so it is reliable for stereo data. However, the pose estimation for an object fails when the object is placed symmetrically to the viewpoint. To overcome this problem, this study proposes a modified viewpoint feature histogram (MVFH) descriptor that consists of two parts: a surface shape component that comprises an extended fast point feature histogram and an extended viewpoint direction component. The MVFH descriptor characterizes an object’s pose and enhances the system’s ability to identify objects with mirrored poses. Finally, the refined pose is further estimated using an iterative closest point when the object has been recognized and the pose roughly estimated by the MVFH descriptor and it has been registered on a database. The estimation results demonstrate that the MVFH feature descriptor allows more accurate pose estimation. The experiments also show that the proposed method can be applied in vision-guided robotic grasping systems. PMID:27886080

  20. Breaking Object Correspondence Across Saccadic Eye Movements Deteriorates Object Recognition.

    PubMed

    Poth, Christian H; Herwig, Arvid; Schneider, Werner X

    2015-01-01

    Visual perception is based on information processing during periods of eye fixations that are interrupted by fast saccadic eye movements. The ability to sample and relate information on task-relevant objects across fixations implies that correspondence between presaccadic and postsaccadic objects is established. Postsaccadic object information usually updates and overwrites information on the corresponding presaccadic object. The presaccadic object representation is then lost. In contrast, the presaccadic object is conserved when object correspondence is broken. This helps transsaccadic memory but it may impose attentional costs on object recognition. Therefore, we investigated how breaking object correspondence across the saccade affects postsaccadic object recognition. In Experiment 1, object correspondence was broken by a brief postsaccadic blank screen. Observers made a saccade to a peripheral object which was displaced during the saccade. This object reappeared either immediately after the saccade or after the blank screen. Within the postsaccadic object, a letter was briefly presented (terminated by a mask). Observers reported displacement direction and letter identity in different blocks. Breaking object correspondence by blanking improved displacement identification but deteriorated postsaccadic letter recognition. In Experiment 2, object correspondence was broken by changing the object's contrast-polarity. There were no object displacements and observers only reported letter identity. Again, breaking object correspondence deteriorated postsaccadic letter recognition. These findings identify transsaccadic object correspondence as a key determinant of object recognition across the saccade. This is in line with the recent hypothesis that breaking object correspondence results in separate representations of presaccadic and postsaccadic objects which then compete for limited attentional processing resources (Schneider, 2013). Postsaccadic object recognition is

  1. Image analysis in unmanned aerial vehicle on-board system for objects detection and recognition with the help of energy characteristics based on wavelet transform

    NASA Astrophysics Data System (ADS)

    Shleymovich, M. P.; Medvedev, M. V.; Lyasheva, S. A.

    2017-04-01

    In this article the problem of image analysis in unmanned aerial vehicle on-board system for objects detection and recognition with the help of energy characteristics based on wavelet transform is described. The approach of salient points extraction based on wavelet transform is proposed. The salience of the points is substantiated with the energy estimates of their weights. On the basis of wavelet transform salient points extraction the method of image contour segmentation is proposed. For further image recognition the salient points descriptors constructed with the help of wavelet transform are used. The objects detection and recognition system for unmanned aerial vehicles based on proposed methods is simulated using the simulation platform.

  2. Breaking Object Correspondence Across Saccadic Eye Movements Deteriorates Object Recognition

    PubMed Central

    Poth, Christian H.; Herwig, Arvid; Schneider, Werner X.

    2015-01-01

    Visual perception is based on information processing during periods of eye fixations that are interrupted by fast saccadic eye movements. The ability to sample and relate information on task-relevant objects across fixations implies that correspondence between presaccadic and postsaccadic objects is established. Postsaccadic object information usually updates and overwrites information on the corresponding presaccadic object. The presaccadic object representation is then lost. In contrast, the presaccadic object is conserved when object correspondence is broken. This helps transsaccadic memory but it may impose attentional costs on object recognition. Therefore, we investigated how breaking object correspondence across the saccade affects postsaccadic object recognition. In Experiment 1, object correspondence was broken by a brief postsaccadic blank screen. Observers made a saccade to a peripheral object which was displaced during the saccade. This object reappeared either immediately after the saccade or after the blank screen. Within the postsaccadic object, a letter was briefly presented (terminated by a mask). Observers reported displacement direction and letter identity in different blocks. Breaking object correspondence by blanking improved displacement identification but deteriorated postsaccadic letter recognition. In Experiment 2, object correspondence was broken by changing the object’s contrast-polarity. There were no object displacements and observers only reported letter identity. Again, breaking object correspondence deteriorated postsaccadic letter recognition. These findings identify transsaccadic object correspondence as a key determinant of object recognition across the saccade. This is in line with the recent hypothesis that breaking object correspondence results in separate representations of presaccadic and postsaccadic objects which then compete for limited attentional processing resources (Schneider, 2013). Postsaccadic object recognition

  3. Recognition memory impairments caused by false recognition of novel objects.

    PubMed

    Yeung, Lok-Kin; Ryan, Jennifer D; Cowell, Rosemary A; Barense, Morgan D

    2013-11-01

    A fundamental assumption underlying most current theories of amnesia is that memory impairments arise because previously studied information either is lost rapidly or is made inaccessible (i.e., the old information appears to be new). Recent studies in rodents have challenged this view, suggesting instead that under conditions of high interference, recognition memory impairments following medial temporal lobe damage arise because novel information appears as though it has been previously seen. Here, we developed a new object recognition memory paradigm that distinguished whether object recognition memory impairments were driven by previously viewed objects being treated as if they were novel or by novel objects falsely recognized as though they were previously seen. In this indirect, eyetracking-based passive viewing task, older adults at risk for mild cognitive impairment showed false recognition to high-interference novel items (with a significant degree of feature overlap with previously studied items) but normal novelty responses to low-interference novel items (with a lower degree of feature overlap). The indirect nature of the task minimized the effects of response bias and other memory-based decision processes, suggesting that these factors cannot solely account for false recognition. These findings support the counterintuitive notion that recognition memory impairments in this memory-impaired population are not characterized by forgetting but rather are driven by the failure to differentiate perceptually similar objects, leading to the false recognition of novel objects as having been seen before.

  4. CT Image Sequence Analysis for Object Recognition - A Rule-Based 3-D Computer Vision System

    Treesearch

    Dongping Zhu; Richard W. Conners; Daniel L. Schmoldt; Philip A. Araman

    1991-01-01

    Research is now underway to create a vision system for hardwood log inspection using a knowledge-based approach. In this paper, we present a rule-based, 3-D vision system for locating and identifying wood defects using topological, geometric, and statistical attributes. A number of different features can be derived from the 3-D input scenes. These features and evidence...

  5. Unposed Object Recognition using an Active Approach

    DTIC Science & Technology

    2013-02-01

    viewpoints when it is necessary to gain con dence in the classi cation decision. We demonstrate the e ect of unposed objects on a state-of-the-art approach to...object recognition, then show how an active approach can increase accuracy. The active approach works by attaching con dence to recognition...prompting further inspection when con dence is low. We demonstrate a performance increase on a wide variety of objects from the RGB-D database, showing a

  6. Object and event recognition for stroke rehabilitation

    NASA Astrophysics Data System (ADS)

    Ghali, Ahmed; Cunningham, Andrew S.; Pridmore, Tony P.

    2003-06-01

    Stroke is a major cause of disability and health care expenditure around the world. Existing stroke rehabilitation methods can be effective but are costly and need to be improved. Even modest improvements in the effectiveness of rehabilitation techniques could produce large benefits in terms of quality of life. The work reported here is part of an ongoing effort to integrate virtual reality and machine vision technologies to produce innovative stroke rehabilitation methods. We describe a combined object recognition and event detection system that provides real time feedback to stroke patients performing everyday kitchen tasks necessary for independent living, e.g. making a cup of coffee. The image plane position of each object, including the patient"s hand, is monitored using histogram-based recognition methods. The relative positions of hand and objects are then reported to a task monitor that compares the patient"s actions against a model of the target task. A prototype system has been constructed and is currently undergoing technical and clinical evaluation.

  7. Neural network system for 3-D object recognition and pose estimation from a single arbitrary 2-D view

    NASA Astrophysics Data System (ADS)

    Khotanzad, Alireza R.; Liou, James H.

    1992-09-01

    In this paper, a robust, and fast system for recognition as well as pose estimation of a 3-D object from a single 2-D perspective of it taken from an arbitrary viewpoint is developed. The approach is invariant to location, orientation, and scale of the object in the perspective. The silhouette of the object in the 2-D perspective is first normalized with respect to location and scale. A set of rotation invariant features derived from complex and orthogonal pseudo- Zernike moments of the image are then extracted. The next stage includes a bank of multilayer feed-forward neural networks (NN) each of which classifies the extracted features. The training set for these nets consists of perspective views of each object taken from several different viewing angles. The NNs in the bank differ in the size of their hidden layer nodes as well as their initial conditions but receive the same input. The classification decisions of all the nets are combined through a majority voting scheme. It is shown that this collective decision making yields better results compared to a single NN operating alone. After the object is classified, two of its pose parameters, namely elevation and aspect angles, are estimated by another module of NNs in a two-stage process. The first stage identifies the likely region of the space that the object is being viewed from. In the second stage, an NN estimator for the identified region is used to compute the pose angles. Extensive experimental studies involving clean and noisy images of seven military ground vehicles are carried out. The performance is compared to two other traditional methods, namely a nearest neighbor rule and a binary decision tree classifier and it is shown that our approach has major advantages over them.

  8. The Role of Object Recognition in Young Infants' Object Segregation.

    ERIC Educational Resources Information Center

    Carey, Susan; Williams, Travis

    2001-01-01

    Discusses Needham's findings by asserting that they extend understanding of infant perception by showing that the memory representations infants draw upon have bound together information about shape, color, and pattern. Considers the distinction between two senses of "recognition" and asks in which sense object recognition contributes to object…

  9. The Role of Object Recognition in Young Infants' Object Segregation.

    ERIC Educational Resources Information Center

    Carey, Susan; Williams, Travis

    2001-01-01

    Discusses Needham's findings by asserting that they extend understanding of infant perception by showing that the memory representations infants draw upon have bound together information about shape, color, and pattern. Considers the distinction between two senses of "recognition" and asks in which sense object recognition contributes to object…

  10. Object Recognition Memory and the Rodent Hippocampus

    ERIC Educational Resources Information Center

    Broadbent, Nicola J.; Gaskin, Stephane; Squire, Larry R.; Clark, Robert E.

    2010-01-01

    In rodents, the novel object recognition task (NOR) has become a benchmark task for assessing recognition memory. Yet, despite its widespread use, a consensus has not developed about which brain structures are important for task performance. We assessed both the anterograde and retrograde effects of hippocampal lesions on performance in the NOR…

  11. Object Recognition Memory and the Rodent Hippocampus

    ERIC Educational Resources Information Center

    Broadbent, Nicola J.; Gaskin, Stephane; Squire, Larry R.; Clark, Robert E.

    2010-01-01

    In rodents, the novel object recognition task (NOR) has become a benchmark task for assessing recognition memory. Yet, despite its widespread use, a consensus has not developed about which brain structures are important for task performance. We assessed both the anterograde and retrograde effects of hippocampal lesions on performance in the NOR…

  12. BDNF controls object recognition memory reconsolidation.

    PubMed

    Radiske, Andressa; Rossato, Janine I; Gonzalez, Maria Carolina; Köhler, Cristiano A; Bevilaqua, Lia R; Cammarota, Martín

    2017-03-06

    Reconsolidation restabilizes memory after reactivation. Previously, we reported that the hippocampus is engaged in object recognition memory reconsolidation to allow incorporation of new information into the original engram. Here we show that BDNF is sufficient for this process, and that blockade of BDNF function in dorsal CA1 impairs updating of the reactivated recognition memory trace.

  13. Increasing the object recognition distance of compact open air on board vision system

    NASA Astrophysics Data System (ADS)

    Kirillov, Sergey; Kostkin, Ivan; Strotov, Valery; Dmitriev, Vladimir; Berdnikov, Vadim; Akopov, Eduard; Elyutin, Aleksey

    2016-10-01

    The aim of this work was developing an algorithm eliminating the atmospheric distortion and improves image quality. The proposed algorithm is entirely software without using additional hardware photographic equipment. . This algorithm does not required preliminary calibration. It can work equally effectively with the images obtained at a distances from 1 to 500 meters. An algorithm for the open air images improve designed for Raspberry Pi model B on-board vision systems is proposed. The results of experimental examination are given.

  14. Automatic anatomy recognition of sparse objects

    NASA Astrophysics Data System (ADS)

    Zhao, Liming; Udupa, Jayaram K.; Odhner, Dewey; Wang, Huiqian; Tong, Yubing; Torigian, Drew A.

    2015-03-01

    A general body-wide automatic anatomy recognition (AAR) methodology was proposed in our previous work based on hierarchical fuzzy models of multitudes of objects which was not tied to any specific organ system, body region, or image modality. That work revealed the challenges encountered in modeling, recognizing, and delineating sparse objects throughout the body (compared to their non-sparse counterparts) if the models are based on the object's exact geometric representations. The challenges stem mainly from the variation in sparse objects in their shape, topology, geographic layout, and relationship to other objects. That led to the idea of modeling sparse objects not from the precise geometric representations of their samples but by using a properly designed optimal super form. This paper presents the underlying improved methodology which includes 5 steps: (a) Collecting image data from a specific population group G and body region Β and delineating in these images the objects in Β to be modeled; (b) Building a super form, S-form, for each object O in Β; (c) Refining the S-form of O to construct an optimal (minimal) super form, S*-form, which constitutes the (fuzzy) model of O; (d) Recognizing objects in Β using the S*-form; (e) Defining confounding and background objects in each S*-form for each object and performing optimal delineation. Our evaluations based on 50 3D computed tomography (CT) image sets in the thorax on four sparse objects indicate that substantially improved performance (FPVF~2%, FNVF~10%, and success where the previous approach failed) can be achieved using the new approach.

  15. Prosopagnosia and object agnosia without covert recognition.

    PubMed

    Newcombe, F; Young, A W; De Haan, E H

    1989-01-01

    Investigations of the visual recognition abilities of the patient M.S. are reported. M.S. is unable to achieve overt recognition of any familiar faces, and many everyday objects. In Task 1 he showed semantic priming from name primes but not from face primes in a name recognition task. In Task 2 he showed no advantage in learning true (face + correct name) rather than untrue (face + someone else's name) pairings of faces and names. In Task 3 semantic priming of lexical decision was only found for object picture primes that M.S. was able to recognize overtly. In Task 4 faster matching of photographs of familiar than unfamiliar objects was only found for objects that M.S. was able to recognize overtly. These findings demonstrate an absence of covert recognition effects for M.S., consistent with the view that his impairment is primarily "perceptual" in nature.

  16. Neural-Network Object-Recognition Program

    NASA Technical Reports Server (NTRS)

    Spirkovska, L.; Reid, M. B.

    1993-01-01

    HONTIOR computer program implements third-order neural network exhibiting invariance under translation, change of scale, and in-plane rotation. Invariance incorporated directly into architecture of network. Only one view of each object needed to train network for two-dimensional-translation-invariant recognition of object. Also used for three-dimensional-transformation-invariant recognition by training network on only set of out-of-plane rotated views. Written in C language.

  17. Object recognition using coding schemes

    NASA Astrophysics Data System (ADS)

    Sadjadi, Firooz A.

    1992-12-01

    A new technique for recognizing two-dimensional objects independent of scale and orientation is presented. This technique's performance on real imagery of tactical military targets, both occluded and nonoccluded, is evaluated. The robustness of this method with respect to partial occlusion is shown. The relatively small storage requirements and fast search time make it an attractive candidate for real-time applications.

  18. Object recognition using coding schemes

    NASA Astrophysics Data System (ADS)

    Sadjadi, Firooz A.

    1991-08-01

    A new technique for recognizing two-dimensional objects independent of scale and orientation is presented. This technique's performance on real imagery of tactical military targets, both occluded and nonoccluded, is evaluated. This study shows that this method is robust with respect to partial occlusion. The relatively small storage requirements and fast search time make it an attractive candidate for real-time applications.

  19. Object Recognition Using Range Images.

    DTIC Science & Technology

    1985-12-01

    Modeling the Dropouts in Range Images 28 Repairing the Pixel Dropouts 33 III. Recognizing Objects from Range Scenes 38 Using Range Geometry for Scene...well as possible methods of correcting for these effects. Other factors af- fecting the correlation coefficient that were considered were pixel dropouts ...and the beam spot size of the laser. Pixel dropouts were shown to be detrimental to a range image’s correlation coefficient, but could be corrected

  20. Object recognition approach based on feature fusion

    NASA Astrophysics Data System (ADS)

    Wang, Runsheng

    2001-09-01

    Multi-sensor information fusion plays an important pole in object recognition and many other application fields. Fusion performance is tightly depended on the fusion level selected and the approach used. Feature level fusion is a potential and difficult fusion level though there might be mainly three fusion levels. Two schemes are developed for key issues of feature level fusion in this paper. In feature selecting, a normal method developed is to analyze the mutual relationship among the features that can be used, and to be applied to order features. In object recognition, a multi-level recognition scheme is developed, whose procedure can be controlled and updated by analyzing the decision result obtained in order to achieve a final reliable result. The new approach is applied to recognize work-piece objects with twelve classes in optical images and open-country objects with four classes based on infrared image sequence and MMW radar. Experimental results are satisfied.

  1. Affordance-based 3D feature for generic object recognition

    NASA Astrophysics Data System (ADS)

    Iizuka, M.; Akizuki, S.; Hashimoto, M.

    2017-03-01

    Techniques for generic object recognition, which targets everyday objects such as cups and spoons, and techniques for approach vector estimation (e.g. estimating grasp position), which are needed for carrying out tasks involving everyday objects, are considered necessary for the perceptual system of service robots. In this research, we design feature for generic object recognition so they can also be applied to approach vector estimation. To carry out tasks involving everyday objects, estimating the function of the target object is critical. Also, as the function of holding liquid is found in all cups, so a function is shared in each type (class) of everyday objects. We thus propose a generic object recognition method that can estimate the approach vector by expressing an object's function as feature. In a test of the generic object recognition of everyday objects, we confirmed that our proposed method had a 92% recognition rate. This rate was 11% higher than the mainstream generic object recognition technique of using convolutional neural network (CNN).

  2. The role of nitric oxide in the object recognition memory.

    PubMed

    Pitsikas, Nikolaos

    2015-05-15

    The novel object recognition task (NORT) assesses recognition memory in animals. It is a non-rewarded paradigm that it is based on spontaneous exploratory behavior in rodents. This procedure is widely used for testing the effects of compounds on recognition memory. Recognition memory is a type of memory severely compromised in schizophrenic and Alzheimer's disease patients. Nitric oxide (NO) is sought to be an intra- and inter-cellular messenger in the central nervous system and its implication in learning and memory is well documented. Here I intended to critically review the role of NO-related compounds on different aspects of recognition memory. Current analysis shows that both NO donors and NO synthase (NOS) inhibitors are involved in object recognition memory and suggests that NO might be a promising target for cognition impairments. However, the potential neurotoxicity of NO would add a note of caution in this context.

  3. Possibility of object recognition using Altera's model based design approach

    NASA Astrophysics Data System (ADS)

    Tickle, A. J.; Wu, F.; Harvey, P. K.; Smith, J. S.

    2009-07-01

    Object recognition is an image processing task of finding a given object in a selected image or video sequence. Object recognition can be divided into two areas: one of these is decision-theoretic and deals with patterns described by quantitative descriptors, for example such as length, area, shape and texture. With this Graphical User Interface Circuitry (GUIC) methodology employed here being relatively new for object recognition systems, the aim of this work is to identify if the developed circuitry can detect certain shapes or strings within the target image. A much smaller reference image feeds the preset data for identification, tests are conducted for both binary and greyscale and the additional mathematical morphology to highlight the area within the target image with the object(s) are located is also presented. This then provides proof that basic recognition methods are valid and would allow the progression to developing decision-theoretical and learning based approaches using GUICs for use in multidisciplinary tasks.

  4. Recognition of object domain by color distribution

    NASA Technical Reports Server (NTRS)

    Mugitani, Takako; Mifune, Mitsuru; Nagata, Shigeki

    1988-01-01

    For the image processing of an object in its natural image, it is necessary to extract in advance the object to be processed from its image. To accomplish this the outer shape of an object is extracted through human instructions, which requires a great deal of time and patience. A method involving the setting of a model of color distribution on the surface of an object is described. This method automatically provides color recognition, a piece of knowledge that represents the properties of an object, from its natural image. A method for recognizing and extracting the object in the image according to the color recognized is also described.

  5. Integration trumps selection in object recognition.

    PubMed

    Saarela, Toni P; Landy, Michael S

    2015-03-30

    Finding and recognizing objects is a fundamental task of vision. Objects can be defined by several "cues" (color, luminance, texture, etc.), and humans can integrate sensory cues to improve detection and recognition [1-3]. Cortical mechanisms fuse information from multiple cues [4], and shape-selective neural mechanisms can display cue invariance by responding to a given shape independent of the visual cue defining it [5-8]. Selective attention, in contrast, improves recognition by isolating a subset of the visual information [9]. Humans can select single features (red or vertical) within a perceptual dimension (color or orientation), giving faster and more accurate responses to items having the attended feature [10, 11]. Attention elevates neural responses and sharpens neural tuning to the attended feature, as shown by studies in psychophysics and modeling [11, 12], imaging [13-16], and single-cell and neural population recordings [17, 18]. Besides single features, attention can select whole objects [19-21]. Objects are among the suggested "units" of attention because attention to a single feature of an object causes the selection of all of its features [19-21]. Here, we pit integration against attentional selection in object recognition. We find, first, that humans can integrate information near optimally from several perceptual dimensions (color, texture, luminance) to improve recognition. They cannot, however, isolate a single dimension even when the other dimensions provide task-irrelevant, potentially conflicting information. For object recognition, it appears that there is mandatory integration of information from multiple dimensions of visual experience. The advantage afforded by this integration, however, comes at the expense of attentional selection.

  6. Integration trumps selection in object recognition

    PubMed Central

    Saarela, Toni P.; Landy, Michael S.

    2015-01-01

    Summary Finding and recognizing objects is a fundamental task of vision. Objects can be defined by several “cues” (color, luminance, texture etc.), and humans can integrate sensory cues to improve detection and recognition [1–3]. Cortical mechanisms fuse information from multiple cues [4], and shape-selective neural mechanisms can display cue-invariance by responding to a given shape independent of the visual cue defining it [5–8]. Selective attention, in contrast, improves recognition by isolating a subset of the visual information [9]. Humans can select single features (red or vertical) within a perceptual dimension (color or orientation), giving faster and more accurate responses to items having the attended feature [10,11]. Attention elevates neural responses and sharpens neural tuning to the attended feature, as shown by studies in psychophysics and modeling [11,12], imaging [13–16], and single-cell and neural population recordings [17,18]. Besides single features, attention can select whole objects [19–21]. Objects are among the suggested “units” of attention because attention to a single feature of an object causes the selection of all of its features [19–21]. Here, we pit integration against attentional selection in object recognition. We find, first, that humans can integrate information near-optimally from several perceptual dimensions (color, texture, luminance) to improve recognition. They cannot, however, isolate a single dimension even when the other dimensions provide task-irrelevant, potentially conflicting information. For object recognition, it appears that there is mandatory integration of information from multiple dimensions of visual experience. The advantage afforded by this integration, however, comes at the expense of attentional selection. PMID:25802154

  7. Divergent short- and long-term effects of acute stress in object recognition memory are mediated by endogenous opioid system activation.

    PubMed

    Nava-Mesa, Mauricio O; Lamprea, Marisol R; Múnera, Alejandro

    2013-11-01

    Acute stress induces short-term object recognition memory impairment and elicits endogenous opioid system activation. The aim of this study was thus to evaluate whether opiate system activation mediates the acute stress-induced object recognition memory changes. Adult male Wistar rats were trained in an object recognition task designed to test both short- and long-term memory. Subjects were randomly assigned to receive an intraperitoneal injection of saline, 1 mg/kg naltrexone or 3 mg/kg naltrexone, four and a half hours before the sample trial. Five minutes after the injection, half the subjects were submitted to movement restraint during four hours while the other half remained in their home cages. Non-stressed subjects receiving saline (control) performed adequately during the short-term memory test, while stressed subjects receiving saline displayed impaired performance. Naltrexone prevented such deleterious effect, in spite of the fact that it had no intrinsic effect on short-term object recognition memory. Stressed subjects receiving saline and non-stressed subjects receiving naltrexone performed adequately during the long-term memory test; however, control subjects as well as stressed subjects receiving a high dose of naltrexone performed poorly. Control subjects' dissociated performance during both memory tests suggests that the short-term memory test induced a retroactive interference effect mediated through light opioid system activation; such effect was prevented either by low dose naltrexone administration or by strongly activating the opioid system through acute stress. Both short-term memory retrieval impairment and long-term memory improvement observed in stressed subjects may have been mediated through strong opioid system activation, since they were prevented by high dose naltrexone administration. Therefore, the activation of the opioid system plays a dual modulating role in object recognition memory. Copyright © 2013 Elsevier Inc. All rights

  8. Neurocomputational bases of object and face recognition.

    PubMed Central

    Biederman, I; Kalocsai, P

    1997-01-01

    A number of behavioural phenomena distinguish the recognition of faces and objects, even when members of a set of objects are highly similar. Because faces have the same parts in approximately the same relations, individuation of faces typically requires specification of the metric variation in a holistic and integral representation of the facial surface. The direct mapping of a hypercolumn-like pattern of activation onto a representation layer that preserves relative spatial filter values in a two-dimensional (2D) coordinate space, as proposed by C. von der Malsburg and his associates, may account for many of the phenomena associated with face recognition. An additional refinement, in which each column of filters (termed a 'jet') is centred on a particular facial feature (or fiducial point), allows selectivity of the input into the holistic representation to avoid incorporation of occluding or nearby surfaces. The initial hypercolumn representation also characterizes the first stage of object perception, but the image variation for objects at a given location in a 2D coordinate space may be too great to yield sufficient predictability directly from the output of spatial kernels. Consequently, objects can be represented by a structural description specifying qualitative (typically, non-accidental) characterizations of an object's parts, the attributes of the parts, and the relations among the parts, largely based on orientation and depth discontinuities (as shown by Hummel & Biederman). A series of experiments on the name priming or physical matching of complementary images (in the Fourier domain) of objects and faces documents that whereas face recognition is strongly dependent on the original spatial filter values, evidence from object recognition indicates strong invariance to these values, even when distinguishing among objects that are as similar as faces. PMID:9304687

  9. Object recognition difficulty in visual apperceptive agnosia.

    PubMed

    Grossman, M; Galetta, S; D'Esposito, M

    1997-04-01

    Two patients with visual apperceptive agnosia were examined on tasks assessing the appreciation of visual material. Elementary visual functioning was relatively preserved, but they had profound difficulty recognizing and naming line drawings. More detailed evaluation revealed accurate recognition of regular geometric shapes and colors, but performance deteriorated when the shapes were made more complex visually, when multiple-choice arrays contained larger numbers of simple targets and foils, and when a mental manipulation such as a rotation was required. The recognition of letters and words was similarly compromised. Naming, recognition, and anomaly judgments of colored pictures and real objects were more accurate than similar decisions involving black-and-white line drawings. Visual imagery for shapes, letters, and objects appeared to be more accurate than visual perception of the same materials. We hypothesize that object recognition difficulty in visual apperceptive agnosia is due to two related factors: the impaired appreciation of the visual perceptual features that constitute objects, and a limitation in the cognitive resources that are available for processing demanding material within the visual modality.

  10. The Functional Architecture of Visual Object Recognition

    DTIC Science & Technology

    1991-07-01

    different forms of agnosia can provide clues to the representations underlying normal object recognition (Farah, 1990). For example, the pair-wise...patterns of deficit and sparing occur. In a review of 99 published cases of agnosia , the observed patterns of co- occurrence implicated two underlying

  11. High speed optical object recognition processor with massive holographic memory

    NASA Technical Reports Server (NTRS)

    Chao, T.; Zhou, H.; Reyes, G.

    2002-01-01

    Real-time object recognition using a compact grayscale optical correlator will be introduced. A holographic memory module for storing a large bank of optimum correlation filters, to accommodate the large data throughput rate needed for many real-world applications, has also been developed. System architecture of the optical processor and the holographic memory will be presented. Application examples of this object recognition technology will also be demonstrated.

  12. Parallel and distributed computation for fault-tolerant object recognition

    NASA Technical Reports Server (NTRS)

    Wechsler, Harry

    1988-01-01

    The distributed associative memory (DAM) model is suggested for distributed and fault-tolerant computation as it relates to object recognition tasks. The fault-tolerance is with respect to geometrical distortions (scale and rotation), noisy inputs, occulsion/overlap, and memory faults. An experimental system was developed for fault-tolerant structure recognition which shows the feasibility of such an approach. The approach is futher extended to the problem of multisensory data integration and applied successfully to the recognition of colored polyhedral objects.

  13. Shape and Color Features for Object Recognition Search

    NASA Technical Reports Server (NTRS)

    Duong, Tuan A.; Duong, Vu A.; Stubberud, Allen R.

    2012-01-01

    A bio-inspired shape feature of an object of interest emulates the integration of the saccadic eye movement and horizontal layer in vertebrate retina for object recognition search where a single object can be used one at a time. The optimal computational model for shape-extraction-based principal component analysis (PCA) was also developed to reduce processing time and enable the real-time adaptive system capability. A color feature of the object is employed as color segmentation to empower the shape feature recognition to solve the object recognition in the heterogeneous environment where a single technique - shape or color - may expose its difficulties. To enable the effective system, an adaptive architecture and autonomous mechanism were developed to recognize and adapt the shape and color feature of the moving object. The bio-inspired object recognition based on bio-inspired shape and color can be effective to recognize a person of interest in the heterogeneous environment where the single technique exposed its difficulties to perform effective recognition. Moreover, this work also demonstrates the mechanism and architecture of the autonomous adaptive system to enable the realistic system for the practical use in the future.

  14. Object recognition with hierarchical discriminant saliency networks

    PubMed Central

    Han, Sunhyoung; Vasconcelos, Nuno

    2014-01-01

    The benefits of integrating attention and object recognition are investigated. While attention is frequently modeled as a pre-processor for recognition, we investigate the hypothesis that attention is an intrinsic component of recognition and vice-versa. This hypothesis is tested with a recognition model, the hierarchical discriminant saliency network (HDSN), whose layers are top-down saliency detectors, tuned for a visual class according to the principles of discriminant saliency. As a model of neural computation, the HDSN has two possible implementations. In a biologically plausible implementation, all layers comply with the standard neurophysiological model of visual cortex, with sub-layers of simple and complex units that implement a combination of filtering, divisive normalization, pooling, and non-linearities. In a convolutional neural network implementation, all layers are convolutional and implement a combination of filtering, rectification, and pooling. The rectification is performed with a parametric extension of the now popular rectified linear units (ReLUs), whose parameters can be tuned for the detection of target object classes. This enables a number of functional enhancements over neural network models that lack a connection to saliency, including optimal feature denoising mechanisms for recognition, modulation of saliency responses by the discriminant power of the underlying features, and the ability to detect both feature presence and absence. In either implementation, each layer has a precise statistical interpretation, and all parameters are tuned by statistical learning. Each saliency detection layer learns more discriminant saliency templates than its predecessors and higher layers have larger pooling fields. This enables the HDSN to simultaneously achieve high selectivity to target object classes and invariance. The performance of the network in saliency and object recognition tasks is compared to those of models from the biological and

  15. Ontogeny of Rat Recognition Memory Measured by the Novel Object Recognition Task

    PubMed Central

    Reger, Maxine L.; Hovda, David A.; Giza, Christopher C.

    2010-01-01

    Detection of novelty is an essential component of recognition memory, which develops throughout cerebral maturation. To better understand the developmental aspects of this memory system, the novel object recognition task (NOR) was used with the immature rat and ontogenically profiled. It was hypothesized that object recognition would vary across development and be inferior to adult performance. The NOR design was made age-appropriate by downsizing the testing objects and arena. Weanling (P20-23), juvenile (P29-40) and adult (P50+) rats were tested after 0.25 hr, 1 hr, 24 hr and 48 hr delays. Weanlings exhibited novel object recognition at 0.25 and 1 hrs, while older animals showed a preference for the novel object out to 24 hrs. These findings are consistent with previous research performed in humans and monkeys, as well as to studies using the NOR after medial temporal lobe damage in adult rats. PMID:19739136

  16. [Neural mechanisms for object and color recognition].

    PubMed

    Koyama, Shinichi; Kawamura, Mitsuru

    2007-01-01

    We reported double-dissociation between the visual processing of the edges and the surfaces of objects. Patients with lateral occipital damage showed selective impairment in the perception of edges whereas those with medial ventral occipital damage showed selective impairment in the perception of the 3D structure of the surface. Patients with medial ventral occipital damage also exhibited impaired perception of color, which is also a surface property. Those results were consistent with those from neuroimaging studies. Taken together, those studies suggest that objects may be processed in two separate pathways in the ventral occipital cortex: the edges of objects are processed in the lateral pathway and the surface of objects are processed in the medial pathway. Both edges and surfaces play important roles in object recognition, and both types of perception should be evaluated in patients with visual agnosia.

  17. 3D object recognition based on local descriptors

    NASA Astrophysics Data System (ADS)

    Jakab, Marek; Benesova, Wanda; Racev, Marek

    2015-01-01

    In this paper, we propose an enhanced method of 3D object description and recognition based on local descriptors using RGB image and depth information (D) acquired by Kinect sensor. Our main contribution is focused on an extension of the SIFT feature vector by the 3D information derived from the depth map (SIFT-D). We also propose a novel local depth descriptor (DD) that includes a 3D description of the key point neighborhood. Thus defined the 3D descriptor can then enter the decision-making process. Two different approaches have been proposed, tested and evaluated in this paper. First approach deals with the object recognition system using the original SIFT descriptor in combination with our novel proposed 3D descriptor, where the proposed 3D descriptor is responsible for the pre-selection of the objects. Second approach demonstrates the object recognition using an extension of the SIFT feature vector by the local depth description. In this paper, we present the results of two experiments for the evaluation of the proposed depth descriptors. The results show an improvement in accuracy of the recognition system that includes the 3D local description compared with the same system without the 3D local description. Our experimental system of object recognition is working near real-time.

  18. A new method of edge detection for object recognition

    USGS Publications Warehouse

    Maddox, Brian G.; Rhew, Benjamin

    2004-01-01

    Traditional edge detection systems function by returning every edge in an input image. This can result in a large amount of clutter and make certain vectorization algorithms less accurate. Accuracy problems can then have a large impact on automated object recognition systems that depend on edge information. A new method of directed edge detection can be used to limit the number of edges returned based on a particular feature. This results in a cleaner image that is easier for vectorization. Vectorized edges from this process could then feed an object recognition system where the edge data would also contain information as to what type of feature it bordered.

  19. Risperidone reverses the spatial object recognition impairment and hippocampal BDNF-TrkB signalling system alterations induced by acute MK-801 treatment

    PubMed Central

    Chen, Guangdong; Lin, Xiaodong; Li, Gongying; Jiang, Diego; Lib, Zhiruo; Jiang, Ronghuan; Zhuo, Chuanjun

    2017-01-01

    The aim of the present study was to investigate the effects of a commonly-used atypical antipsychotic, risperidone, on alterations in spatial learning and in the hippocampal brain-derived neurotrophic factor (BDNF)-tyrosine receptor kinase B (TrkB) signalling system caused by acute dizocilpine maleate (MK-801) treatment. In experiment 1, adult male Sprague-Dawley rats subjected to acute treatment of either low-dose MK801 (0.1 mg/kg) or normal saline (vehicle) were tested for spatial object recognition and hippocampal expression levels of BDNF, TrkB and the phophorylation of TrkB (p-TrkB). We found that compared to the vehicle, MK-801 treatment impaired spatial object recognition of animals and downregulated the expression levels of p-TrkB. In experiment 2, MK-801- or vehicle-treated animals were further injected with risperidone (0.1 mg/kg) or vehicle before behavioural testing and sacrifice. Of note, we found that risperidone successfully reversed the deleterious effects of MK-801 on spatial object recognition and upregulated the hippocampal BDNF-TrkB signalling system. Collectively, the findings suggest that cognitive deficits from acute N-methyl-D-aspartate receptor blockade may be associated with the hypofunction of hippocampal BDNF-TrkB signalling system and that risperidone was able to reverse these alterations. PMID:28451387

  20. Risperidone reverses the spatial object recognition impairment and hippocampal BDNF-TrkB signalling system alterations induced by acute MK-801 treatment.

    PubMed

    Chen, Guangdong; Lin, Xiaodong; Li, Gongying; Jiang, Diego; Lib, Zhiruo; Jiang, Ronghuan; Zhuo, Chuanjun

    2017-03-01

    The aim of the present study was to investigate the effects of a commonly-used atypical antipsychotic, risperidone, on alterations in spatial learning and in the hippocampal brain-derived neurotrophic factor (BDNF)-tyrosine receptor kinase B (TrkB) signalling system caused by acute dizocilpine maleate (MK-801) treatment. In experiment 1, adult male Sprague-Dawley rats subjected to acute treatment of either low-dose MK801 (0.1 mg/kg) or normal saline (vehicle) were tested for spatial object recognition and hippocampal expression levels of BDNF, TrkB and the phophorylation of TrkB (p-TrkB). We found that compared to the vehicle, MK-801 treatment impaired spatial object recognition of animals and downregulated the expression levels of p-TrkB. In experiment 2, MK-801- or vehicle-treated animals were further injected with risperidone (0.1 mg/kg) or vehicle before behavioural testing and sacrifice. Of note, we found that risperidone successfully reversed the deleterious effects of MK-801 on spatial object recognition and upregulated the hippocampal BDNF-TrkB signalling system. Collectively, the findings suggest that cognitive deficits from acute N-methyl-D-aspartate receptor blockade may be associated with the hypofunction of hippocampal BDNF-TrkB signalling system and that risperidone was able to reverse these alterations.

  1. Where you look can influence haptic object recognition.

    PubMed

    Lawson, Rebecca; Boylan, Amy; Edwards, Lauren

    2014-02-01

    We investigated whether the relative position of objects and the body would influence haptic recognition. People felt objects on the right or left side of their body midline, using their right hand. Their head was turned towards or away from the object, and they could not see their hands or the object. People were better at naming 2-D raised line drawings and 3-D small-scale models of objects and also real, everyday objects when they looked towards them. However, this head-towards benefit was reliable only when their right hand crossed their body midline to feel objects on their left side. Thus, haptic object recognition was influenced by people's head position, although vision of their hand and the object was blocked. This benefit of turning the head towards the object being explored suggests that proprioceptive and haptic inputs are remapped into an external coordinate system and that this remapping is harder when the body is in an unusual position (with the hand crossing the body midline and the head turned away from the hand). The results indicate that haptic processes align sensory inputs from the hand and head even though either hand-centered or object-centered coordinate systems should suffice for haptic object recognition.

  2. Perceptual Plasticity for Auditory Object Recognition

    PubMed Central

    Heald, Shannon L. M.; Van Hedger, Stephen C.; Nusbaum, Howard C.

    2017-01-01

    In our auditory environment, we rarely experience the exact acoustic waveform twice. This is especially true for communicative signals that have meaning for listeners. In speech and music, the acoustic signal changes as a function of the talker (or instrument), speaking (or playing) rate, and room acoustics, to name a few factors. Yet, despite this acoustic variability, we are able to recognize a sentence or melody as the same across various kinds of acoustic inputs and determine meaning based on listening goals, expectations, context, and experience. The recognition process relates acoustic signals to prior experience despite variability in signal-relevant and signal-irrelevant acoustic properties, some of which could be considered as “noise” in service of a recognition goal. However, some acoustic variability, if systematic, is lawful and can be exploited by listeners to aid in recognition. Perceivable changes in systematic variability can herald a need for listeners to reorganize perception and reorient their attention to more immediately signal-relevant cues. This view is not incorporated currently in many extant theories of auditory perception, which traditionally reduce psychological or neural representations of perceptual objects and the processes that act on them to static entities. While this reduction is likely done for the sake of empirical tractability, such a reduction may seriously distort the perceptual process to be modeled. We argue that perceptual representations, as well as the processes underlying perception, are dynamically determined by an interaction between the uncertainty of the auditory signal and constraints of context. This suggests that the process of auditory recognition is highly context-dependent in that the identity of a given auditory object may be intrinsically tied to its preceding context. To argue for the flexible neural and psychological updating of sound-to-meaning mappings across speech and music, we draw upon examples

  3. Generalized Sparselet Models for Real-Time Multiclass Object Recognition.

    PubMed

    Song, Hyun Oh; Girshick, Ross; Zickler, Stefan; Geyer, Christopher; Felzenszwalb, Pedro; Darrell, Trevor

    2015-05-01

    The problem of real-time multiclass object recognition is of great practical importance in object recognition. In this paper, we describe a framework that simultaneously utilizes shared representation, reconstruction sparsity, and parallelism to enable real-time multiclass object detection with deformable part models at 5Hz on a laptop computer with almost no decrease in task performance. Our framework is trained in the standard structured output prediction formulation and is generically applicable for speeding up object recognition systems where the computational bottleneck is in multiclass, multi-convolutional inference. We experimentally demonstrate the efficiency and task performance of our method on PASCAL VOC, subset of ImageNet, Caltech101 and Caltech256 dataset.

  4. Infants' recognition of objects using canonical color.

    PubMed

    Kimura, Atsushi; Wada, Yuji; Yang, Jiale; Otsuka, Yumiko; Dan, Ippeita; Masuda, Tomohiro; Kanazawa, So; Yamaguchi, Masami K

    2010-03-01

    We explored infants' ability to recognize the canonical colors of daily objects, including two color-specific objects (human face and fruit) and a non-color-specific object (flower), by using a preferential looking technique. A total of 58 infants between 5 and 8 months of age were tested with a stimulus composed of two color pictures of an object placed side by side: a correctly colored picture (e.g., red strawberry) and an inappropriately colored picture (e.g., green-blue strawberry). The results showed that, overall, the 6- to 8-month-olds showed preference for the correctly colored pictures for color-specific objects, whereas they did not show preference for the correctly colored pictures for the non-color-specific object. The 5-month-olds showed no significant preference for the correctly colored pictures for all object conditions. These findings imply that the recognition of canonical color for objects emerges at 6 months of age. Copyright 2009 Elsevier Inc. All rights reserved.

  5. A Proposed Biologically Inspired Model for Object Recognition

    NASA Astrophysics Data System (ADS)

    Al-Absi, Hamada R. H.; Abdullah, Azween B.

    Object recognition has attracted the attention of many researchers as it is considered as one of the most important problems in computer vision. Two main approaches have been utilized to develop object recognition solutions i.e. machine and biological vision. Many algorithms have been developed in machine vision. Recently, Biology has inspired computer scientist to map the features of the human and primate's visual systems into computational models. Some of these models are based on the feed-forward mechanism of information processing in cortex; however, the performance of these models has been affected by the increase of clutter in the scene. Another mechanism of information processing in cortex is called the feedback. This mechanism has also been mapped into computational models. However, the results were also not satisfying. In this paper an object recognition model based on the integration of the feed-forward and feedback functions in the visual cortex is proposed.

  6. Automatic anatomy recognition via fuzzy object models

    NASA Astrophysics Data System (ADS)

    Udupa, Jayaram K.; Odhner, Dewey; Falcão, Alexandre X.; Ciesielski, Krzysztof C.; Miranda, Paulo A. V.; Matsumoto, Monica; Grevera, George J.; Saboury, Babak; Torigian, Drew A.

    2012-02-01

    To make Quantitative Radiology a reality in routine radiological practice, computerized automatic anatomy recognition (AAR) during radiological image reading becomes essential. As part of this larger goal, last year at this conference we presented a fuzzy strategy for building body-wide group-wise anatomic models. In the present paper, we describe the further advances made in fuzzy modeling and the algorithms and results achieved for AAR by using the fuzzy models. The proposed AAR approach consists of three distinct steps: (a) Building fuzzy object models (FOMs) for each population group G. (b) By using the FOMs to recognize the individual objects in any given patient image I under group G. (c) To delineate the recognized objects in I. This paper will focus mostly on (b). FOMs are built hierarchically, the smaller sub-objects forming the offspring of larger parent objects. The hierarchical pose relationships from the parent to offspring are codified in the FOMs. Several approaches are being explored currently, grouped under two strategies, both being hierarchical: (ra1) those using search strategies; (ra2) those strategizing a one-shot approach by which the model pose is directly estimated without searching. Based on 32 patient CT data sets each from the thorax and abdomen and 25 objects modeled, our analysis indicates that objects do not all scale uniformly with patient size. Even the simplest among the (ra2) strategies of recognizing the root object and then placing all other descendants as per the learned parent-to-offspring pose relationship bring the models on an average within about 18 mm of the true locations.

  7. Optical Recognition And Tracking Of Objects

    NASA Technical Reports Server (NTRS)

    Chao, Tien-Hsin; Liu, Hua-Kuang

    1988-01-01

    Separate objects moving independently tracked simultaneously. System uses coherent optical techniques to obtain correlation between each object and reference image. Moving objects monitored by charge-coupled-device television camera, output fed to liquid-crystal television (LCTV) display. Acting as spatial light modulator, LCTV impresses images of moving objects on collimated laser beam. Beam spatially low-pass filtered to remove high-spatial-frequency television grid pattern.

  8. Aerial Object Recognition Algorithm Based on Contour Descriptor

    NASA Astrophysics Data System (ADS)

    Strotov, V. V.; Babyan, P. V.; Smirnov, S. A.

    2017-05-01

    This paper describes the image recognition algorithm for on-board and stationary vision system. Suggested algorithm is intended to recognize the aerial object of a specific kind using the set of the reference objects defined by 3D models. The proposed algorithm based on the outer contour descriptor building. The algorithm consists of two stages: learning and recognition. Learning stage is devoted to the exploring of reference objects. Using 3D models we can gather set of training images by rendering the 3D model from viewpoints evenly distributed on a sphere. Sphere points distribution is made by the geosphere principle. Gathered training image set is used for calculating descriptors, which will be used in the recognition stage of the algorithm. The recognition stage is focusing on estimating the similarity of the captured object and the reference objects by matching an observed image descriptor and the reference object descriptors. The experimental research was performed using a set of the models of the aircraft of the different types. The proposed orientation estimation algorithm showed good accuracy in all case studies.

  9. Utilization-based object recognition in confined spaces

    NASA Astrophysics Data System (ADS)

    Shirkhodaie, Amir; Telagamsetti, Durga; Chan, Alex L.

    2017-05-01

    Recognizing substantially occluded objects in confined spaces is a very challenging problem for ground-based persistent surveillance systems. In this paper, we discuss the ontology inference of occluded object recognition in the context of in-vehicle group activities (IVGA) and describe an approach that we refer to as utilization-based object recognition method. We examine the performance of three types of classifiers tailored for the recognition of objects with partial visibility, namely, (1) Hausdorff Distance classifier, (2) Hamming Network classifier, and (3) Recurrent Neural Network classifier. In order to train these classifiers, we have generated multiple imagery datasets containing a mixture of common objects appearing inside a vehicle with full or partial visibility and occultation. To generate dynamic interactions between multiple people, we model the IVGA scenarios using a virtual simulation environment, in which a number of simulated actors perform a variety of IVGA tasks independently or jointly. This virtual simulation engine produces the much needed imagery datasets for the verification and validation of the efficiency and effectiveness of the selected object recognizers. Finally, we improve the performance of these object recognizers by incorporating human gestural information that differentiates various object utilization or handling methods through the analyses of dynamic human-object interactions (HOI), human-human interactions (HHI), and human-vehicle interactions (HVI) in the context of IVGA.

  10. Field of attention for instantaneous object recognition.

    PubMed

    Yao, Jian-Gao; Gao, Xin; Yan, Hong-Mei; Li, Chao-Yi

    2011-01-21

    Instantaneous object discrimination and categorization are fundamental cognitive capacities performed with the guidance of visual attention. Visual attention enables selection of a salient object within a limited area of the visual field; we referred to as "field of attention" (FA). Though there is some evidence concerning the spatial extent of object recognition, the following questions still remain unknown: (a) how large is the FA for rapid object categorization, (b) how accuracy of attention is distributed over the FA, and (c) how fast complex objects can be categorized when presented against backgrounds formed by natural scenes. To answer these questions, we used a visual perceptual task in which subjects were asked to focus their attention on a point while being required to categorize briefly flashed (20 ms) photographs of natural scenes by indicating whether or not these contained an animal. By measuring the accuracy of categorization at different eccentricities from the fixation point, we were able to determine the spatial extent and the distribution of accuracy over the FA, as well as the speed of categorizing objects using stimulus onset asynchrony (SOA). Our results revealed that subjects are able to rapidly categorize complex natural images within about 0.1 s without eye movement, and showed that the FA for instantaneous image categorization covers a visual field extending 20° × 24°, and accuracy was highest (>90%) at the center of FA and declined with increasing eccentricity. In conclusion, human beings are able to categorize complex natural images at a glance over a large extent of the visual field without eye movement.

  11. Neural Representations that Support Invariant Object Recognition

    PubMed Central

    Goris, Robbe L. T.; Op de Beeck, Hans P.

    2008-01-01

    Neural mechanisms underlying invariant behaviour such as object recognition are not well understood. For brain regions critical for object recognition, such as inferior temporal cortex (ITC), there is now ample evidence indicating that single cells code for many stimulus aspects, implying that only a moderate degree of invariance is present. However, recent theoretical and empirical work seems to suggest that integrating responses of multiple non-invariant units may produce invariant representations at population level. We provide an explicit test for the hypothesis that a linear read-out mechanism of a pool of units resembling ITC neurons may achieve invariant performance in an identification task. A linear classifier was trained to decode a particular value in a 2-D stimulus space using as input the response pattern across a population of units. Only one dimension was relevant for the task, and the stimulus location on the irrelevant dimension (ID) was kept constant during training. In a series of identification tests, the stimulus location on the relevant dimension (RD) and ID was manipulated, yielding estimates for both the level of sensitivity and tolerance reached by the network. We studied the effects of several single-cell characteristics as well as population characteristics typically considered in the literature, but found little support for the hypothesis. While the classifier averages out effects of idiosyncratic tuning properties and inter-unit variability, its invariance is very much determined by the (hypothetical) ‘average’ neuron. Consequently, even at population level there exists a fundamental trade-off between selectivity and tolerance, and invariant behaviour does not emerge spontaneously. PMID:19242556

  12. Rule-Based Orientation Recognition Of A Moving Object

    NASA Astrophysics Data System (ADS)

    Gove, Robert J.

    1989-03-01

    This paper presents a detailed description and a comparative analysis of the algorithms used to determine the position and orientation of an object in real-time. The exemplary object, a freely moving gold-fish in an aquarium, provides "real-world" motion, with definable characteristics of motion (the fish never swims upside-down) and the complexities of a non-rigid body. For simplicity of implementation, and since a restricted and stationary viewing domain exists (fish-tank), we reduced the problem of obtaining 3D correspondence information to trivial alignment calculations by using two cameras orthogonally viewing the object. We applied symbolic processing techniques to recognize the 3-D orientation of a moving object of known identity in real-time. Assuming motion, each new frame (sensed by the two cameras) provides images of the object's profile which has most likely undergone translation, rotation, scaling and/or bending of the non-rigid object since the previous frame. We developed an expert system which uses heuristics of the object's motion behavior in the form of rules and information obtained via low-level image processing (like numerical inertial axis calculations) to dynamically estimate the object's orientation. An inference engine provides these estimates at frame rates of up to 10 per second (which is essentially real-time). The advantages of the rule-based approach to orientation recognition will be compared other pattern recognition techniques. Our results of an investigation of statistical pattern recognition, neural networks, and procedural techniques for orientation recognition will be included. We implemented the algorithms in a rapid-prototyping environment, the TI-Ezplorer, equipped with an Odyssey and custom imaging hardware. A brief overview of the workstation is included to clarify one motivation for our choice of algorithms. These algorithms exploit two facets of the prototype image processing and understanding workstation - both low

  13. Examining Object Location and Object Recognition Memory in Mice

    PubMed Central

    Vogel-Ciernia, Annie; Wood, Marcelo A.

    2014-01-01

    Unit Introduction The ability to store and recall our life experiences defines a person's identity. Consequently, the loss of long-term memory is a particularly devastating part of a variety of cognitive disorders, diseases and injuries. There is a great need to develop therapeutics to treat memory disorders, and thus a variety of animal models and memory paradigms have been developed. Mouse models have been widely used both to study basic disease mechanisms and to evaluate potential drug targets for therapeutic development. The relative ease of genetic manipulation of Mus musculus has led to a wide variety of genetically altered mice that model cognitive disorders ranging from Alzheimer's disease to autism. Rodents, including mice, are particularly adept at encoding and remembering spatial relationships, and these long-term spatial memories are dependent on the medial temporal lobe of the brain. These brain regions are also some of the first and most heavily impacted in disorders of human memory including Alzheimer's disease. Consequently, some of the simplest and most commonly used tests of long-term memory in mice are those that examine memory for objects and spatial relationships. However, many of these tasks, such as Morris water maze and contextual fear conditioning, are dependent upon the encoding and retrieval of emotionally aversive and inherently stressful training events. While these types of memories are important, they do not reflect the typical day-to-day experiences or memories most commonly affected in human disease. In addition, stress hormone release alone can modulate memory and thus obscure or artificially enhance these types of tasks. To avoid these sorts of confounds, we and many others have utilized tasks testing animals’ memory for object location and novel object recognition. These tasks involve exploiting rodents’ innate preference for novelty, and are inherently not stressful. In this protocol we detail how memory for object location

  14. A Hierarchical Control Strategy For 2-D Object Recognition

    NASA Astrophysics Data System (ADS)

    Cullen, Mark F.; Kuszmaul, Christopher L.; Ramsey, Timothy S.

    1988-02-01

    A control strategy for 2-D object recognition has been implemented on a hardware configuration which includes a Symbolics Lisp Machine (TM) as a front-end processor to a 16,384 processor Connection Machine (TM). The goal of this ongoing research program is to develop an image analysis system as an aid to human image interpretation experts. Our efforts have concentrated on 2-D object recognition in aerial imagery specifically, the detection and identification of aircraft near the Danbury, CT airport. Image processing functions to label and extract image features are implemented on the Connection Machine for robust computation. A model matching function was also designed and implemented on the CM for object recognition. In this paper we report on the integration of these algorithms on the CM, with a hierarchical control strategy to focus and guide the object recognition task to particular objects and regions of interest in imagery. It will be shown that these tech-nigues may be used to manipulate imagery on the order of 2k x 2k pixels in near-real-time.

  15. Reader error, object recognition, and visual search

    NASA Astrophysics Data System (ADS)

    Kundel, Harold L.

    2004-05-01

    Small abnormalities such as hairline fractures, lung nodules and breast tumors are missed by competent radiologists with sufficient frequency to make them a matter of concern to the medical community; not only because they lead to litigation but also because they delay patient care. It is very easy to attribute misses to incompetence or inattention. To do so may be placing an unjustified stigma on the radiologists involved and may allow other radiologists to continue a false optimism that it can never happen to them. This review presents some of the fundamentals of visual system function that are relevant to understanding the search for and the recognition of small targets embedded in complicated but meaningful backgrounds like chests and mammograms. It presents a model for visual search that postulates a pre-attentive global analysis of the retinal image followed by foveal checking fixations and eventually discovery scanning. The model will be used to differentiate errors of search, recognition and decision making. The implications for computer aided diagnosis and for functional workstation design are discussed.

  16. The Role of Perceptual Load in Object Recognition

    ERIC Educational Resources Information Center

    Lavie, Nilli; Lin, Zhicheng; Zokaei, Nahid; Thoma, Volker

    2009-01-01

    Predictions from perceptual load theory (Lavie, 1995, 2005) regarding object recognition across the same or different viewpoints were tested. Results showed that high perceptual load reduces distracter recognition levels despite always presenting distracter objects from the same view. They also showed that the levels of distracter recognition were…

  17. A novel multi-view object recognition in complex background

    NASA Astrophysics Data System (ADS)

    Chang, Yongxin; Yu, Huapeng; Xu, Zhiyong; Fu, Chengyu; Gao, Chunming

    2015-02-01

    Recognizing objects from arbitrary aspects is always a highly challenging problem in computer vision, and most existing algorithms mainly focus on a specific viewpoint research. Hence, in this paper we present a novel recognizing framework based on hierarchical representation, part-based method and learning in order to recognize objects from different viewpoints. The learning evaluates the model's mistakes and feeds it back the detector to avid the same mistakes in the future. The principal idea is to extract intrinsic viewpoint invariant features from the unseen poses of object, and then to take advantage of these shared appearance features to support recognition combining with the improved multiple view model. Compared with other recognition models, the proposed approach can efficiently tackle multi-view problem and promote the recognition versatility of our system. For an quantitative valuation The novel algorithm has been tested on several benchmark datasets such as Caltech 101 and PASCAL VOC 2010. The experimental results validate that our approach can recognize objects more precisely and the performance outperforms others single view recognition methods.

  18. Object Recognition using Feature- and Color-Based Methods

    NASA Technical Reports Server (NTRS)

    Duong, Tuan; Duong, Vu; Stubberud, Allen

    2008-01-01

    An improved adaptive method of processing image data in an artificial neural network has been developed to enable automated, real-time recognition of possibly moving objects under changing (including suddenly changing) conditions of illumination and perspective. The method involves a combination of two prior object-recognition methods one based on adaptive detection of shape features and one based on adaptive color segmentation to enable recognition in situations in which either prior method by itself may be inadequate. The chosen prior feature-based method is known as adaptive principal-component analysis (APCA); the chosen prior color-based method is known as adaptive color segmentation (ACOSE). These methods are made to interact with each other in a closed-loop system to obtain an optimal solution of the object-recognition problem in a dynamic environment. One of the results of the interaction is to increase, beyond what would otherwise be possible, the accuracy of the determination of a region of interest (containing an object that one seeks to recognize) within an image. Another result is to provide a minimized adaptive step that can be used to update the results obtained by the two component methods when changes of color and apparent shape occur. The net effect is to enable the neural network to update its recognition output and improve its recognition capability via an adaptive learning sequence. In principle, the improved method could readily be implemented in integrated circuitry to make a compact, low-power, real-time object-recognition system. It has been proposed to demonstrate the feasibility of such a system by integrating a 256-by-256 active-pixel sensor with APCA, ACOSE, and neural processing circuitry on a single chip. It has been estimated that such a system on a chip would have a volume no larger than a few cubic centimeters, could operate at a rate as high as 1,000 frames per second, and would consume in the order of milliwatts of power.

  19. Automatic Recognition of Object Names in Literature

    NASA Astrophysics Data System (ADS)

    Bonnin, C.; Lesteven, S.; Derriere, S.; Oberto, A.

    2008-08-01

    SIMBAD is a database of astronomical objects that provides (among other things) their bibliographic references in a large number of journals. Currently, these references have to be entered manually by librarians who read each paper. To cope with the increasing number of papers, CDS develops a tool to assist the librarians in their work, taking advantage of the Dictionary of Nomenclature of Celestial Objects, which keeps track of object acronyms and of their origin. The program searches for object names directly in PDF documents by comparing the words with all the formats stored in the Dictionary of Nomenclature. It also searches for variable star names based on constellation names and for a large list of usual names such as Aldebaran or the Crab. Object names found in the documents often correspond to several astronomical objects. The system retrieves all possible matches, displays them with their object type given by SIMBAD, and lets the librarian make the final choice. The bibliographic reference can then be automatically added to the object identifiers in the database. Besides, the systematic usage of the Dictionary of Nomenclature, which is updated manually, permitted to automatically check it and to detect errors and inconsistencies. Last but not least, the program collects some additional information such as the position of the object names in the document (in the title, subtitle, abstract, table, figure caption...) and their number of occurrences. In the future, this will permit to calculate the 'weight' of an object in a reference and to provide SIMBAD users with an important new information, which will help them to find the most relevant papers in the object reference list.

  20. Hippocampal histone acetylation regulates object recognition and the estradiol-induced enhancement of object recognition.

    PubMed

    Zhao, Zaorui; Fan, Lu; Fortress, Ashley M; Boulware, Marissa I; Frick, Karyn M

    2012-02-15

    Histone acetylation has recently been implicated in learning and memory processes, yet necessity of histone acetylation for such processes has not been demonstrated using pharmacological inhibitors of histone acetyltransferases (HATs). As such, the present study tested whether garcinol, a potent HAT inhibitor in vitro, could impair hippocampal memory consolidation and block the memory-enhancing effects of the modulatory hormone 17β-estradiol E2. We first showed that bilateral infusion of garcinol (0.1, 1, or 10 μg/side) into the dorsal hippocampus (DH) immediately after training impaired object recognition memory consolidation in ovariectomized female mice. A behaviorally effective dose of garcinol (10 μg/side) also significantly decreased DH HAT activity. We next examined whether DH infusion of a behaviorally subeffective dose of garcinol (1 ng/side) could block the effects of DH E2 infusion on object recognition and epigenetic processes. Immediately after training, ovariectomized female mice received bilateral DH infusions of vehicle, E2 (5 μg/side), garcinol (1 ng/side), or E2 plus garcinol. Forty-eight hours later, garcinol blocked the memory-enhancing effects of E2. Garcinol also reversed the E2-induced increase in DH histone H3 acetylation, HAT activity, and levels of the de novo methyltransferase DNMT3B, as well as the E2-induced decrease in levels of the memory repressor protein histone deacetylase 2. Collectively, these findings suggest that histone acetylation is critical for object recognition memory consolidation and the beneficial effects of E2 on object recognition. Importantly, this work demonstrates that the role of histone acetylation in memory processes can be studied using a HAT inhibitor.

  1. A new selective developmental deficit: Impaired object recognition with normal face recognition.

    PubMed

    Germine, Laura; Cashdollar, Nathan; Düzel, Emrah; Duchaine, Bradley

    2011-05-01

    Studies of developmental deficits in face recognition, or developmental prosopagnosia, have shown that individuals who have not suffered brain damage can show face recognition impairments coupled with normal object recognition (Duchaine and Nakayama, 2005; Duchaine et al., 2006; Nunn et al., 2001). However, no developmental cases with the opposite dissociation - normal face recognition with impaired object recognition - have been reported. The existence of a case of non-face developmental visual agnosia would indicate that the development of normal face recognition mechanisms does not rely on the development of normal object recognition mechanisms. To see whether a developmental variant of non-face visual object agnosia exists, we conducted a series of web-based object and face recognition tests to screen for individuals showing object recognition memory impairments but not face recognition impairments. Through this screening process, we identified AW, an otherwise normal 19-year-old female, who was then tested in the lab on face and object recognition tests. AW's performance was impaired in within-class visual recognition memory across six different visual categories (guns, horses, scenes, tools, doors, and cars). In contrast, she scored normally on seven tests of face recognition, tests of memory for two other object categories (houses and glasses), and tests of recall memory for visual shapes. Testing confirmed that her impairment was not related to a general deficit in lower-level perception, object perception, basic-level recognition, or memory. AW's results provide the first neuropsychological evidence that recognition memory for non-face visual object categories can be selectively impaired in individuals without brain damage or other memory impairment. These results indicate that the development of recognition memory for faces does not depend on intact object recognition memory and provide further evidence for category-specific dissociations in visual

  2. A Rule-Based Pattern Matching System for the Recognition of Three-Dimensional Line Drawn Objects: A Foundation for Video Tracking,

    DTIC Science & Technology

    1986-01-01

    case, the object could have been a cubical one (prob = 35) or a prism (prob = 15) or a L-shaped object (prob = 25) or a T-shaped object (prob = 25...recognition program was coded in Prolog. A database containing eight object descriptions was used for testing. The set of oojects consisted of prisms , pyramids...practical use, it sfr ild be able to recognize objects in a scene rather than when they are presented individually. This needs the introduction of more

  3. Planning Multiple Observations for Object Recognition

    DTIC Science & Technology

    1992-12-09

    choosing the branch with the highest weight at each level, and backtracking when necessary. The PREMIO system of Camps, et al [51 predicts object...appearances under various conditions of lighting, viewpoint, sensor, and image processing operators. Unlike other systems, PREMIO also evaluates the utility...1988). [51 Camps, 0. 1., Shapiro, L. G., and Haralick, R. M. PREMIO : an overview. Proc. IEEE Workshop on Directions in Automated CAD-Based Vision, pp

  4. Object recognition memory: neurobiological mechanisms of encoding, consolidation and retrieval.

    PubMed

    Winters, Boyer D; Saksida, Lisa M; Bussey, Timothy J

    2008-07-01

    Tests of object recognition memory, or the judgment of the prior occurrence of an object, have made substantial contributions to our understanding of the nature and neurobiological underpinnings of mammalian memory. Only in recent years, however, have researchers begun to elucidate the specific brain areas and neural processes involved in object recognition memory. The present review considers some of this recent research, with an emphasis on studies addressing the neural bases of perirhinal cortex-dependent object recognition memory processes. We first briefly discuss operational definitions of object recognition and the common behavioural tests used to measure it in non-human primates and rodents. We then consider research from the non-human primate and rat literature examining the anatomical basis of object recognition memory in the delayed nonmatching-to-sample (DNMS) and spontaneous object recognition (SOR) tasks, respectively. The results of these studies overwhelmingly favor the view that perirhinal cortex (PRh) is a critical region for object recognition memory. We then discuss the involvement of PRh in the different stages--encoding, consolidation, and retrieval--of object recognition memory. Specifically, recent work in rats has indicated that neural activity in PRh contributes to object memory encoding, consolidation, and retrieval processes. Finally, we consider the pharmacological, cellular, and molecular factors that might play a part in PRh-mediated object recognition memory. Recent studies in rodents have begun to indicate the remarkable complexity of the neural substrates underlying this seemingly simple aspect of declarative memory.

  5. The role of perceptual load in object recognition.

    PubMed

    Lavie, Nilli; Lin, Zhicheng; Zokaei, Nahid; Thoma, Volker

    2009-10-01

    Predictions from perceptual load theory (Lavie, 1995, 2005) regarding object recognition across the same or different viewpoints were tested. Results showed that high perceptual load reduces distracter recognition levels despite always presenting distracter objects from the same view. They also showed that the levels of distracter recognition were unaffected by a change in the distracter object view under conditions of low perceptual load. These results were found both with repetition priming measures of distracter recognition and with performance on a surprise recognition memory test. The results support load theory proposals that distracter recognition critically depends on the level of perceptual load. The implications for the role of attention in object recognition theories are discussed.

  6. Chotosan, a kampo formula, ameliorates chronic cerebral hypoperfusion-induced deficits in object recognition behaviors and central cholinergic systems in mice.

    PubMed

    Zhao, Qi; Murakami, Yukihisa; Tohda, Michihisa; Obi, Ryosuke; Shimada, Yutaka; Matsumoto, Kinzo

    2007-04-01

    We previously demonstrated that the Kampo formula chotosan (CTS) ameliorated spatial cognitive impairment via central cholinergic systems in a chronic cerebral hypoperfusion (P2VO) mouse model. In this study, the object discrimination tasks were used to determine if the ameliorative effects of CTS on P2VO-induced cognitive deficits are a characteristic pharmacological profile of this formula, with the aim of clarifying the mechanisms by which CTS enhances central cholinergic function in P2VO mice. The cholinesterase inhibitor tacrine (THA) and Kampo formula saikokeishito (SKT) were used as controls. P2VO impaired object discrimination performance in the object recognition, location, and context tests. Daily administration of CTS (750 mg/kg, p.o.) and THA (2.5 mg/kg, i.p.) improved the object discrimination deficits, whereas SKT (750 mg/kg, p.o.) did not. In ex vivo assays, tacrine but not CTS or SKT inhibited cortical cholinesterase activity. P2VO reduced the mRNA expression of m(3) and m(5) muscarinic receptors and choline acetyltransferase but not that of other muscarinic receptor subtypes in the cerebral cortex. Daily administration of CTS and THA but not SKT reversed these expression changes. These results suggest that CTS and THA improve P2VO-induced cognitive impairment by normalizing the deficit of central cholinergic systems and that the beneficial effect on P2VO-induced cognitive deficits is a distinctive pharmacological characteristic of CTS.

  7. Shape Recognition Of Complex Objects By Syntactical Primitives

    NASA Astrophysics Data System (ADS)

    Lenger, D.; Cipovic, H.

    1985-04-01

    The paper describes a pattern recognition method based on syntactic image analysis applicable in autonomous systems of robot vision for the purpose of pattern detection or classification. The discrimination of syntactic elements is realized by polygonal approximation of contours employing a very fast algorithm based upon coding, local pixel logic and methods of choice instead of numerical methods. Semantic information is derived from attributes calculated from the filtered shape vector. No a priori information on image objects is required, and the choice of starting point is determined by finding the significant directions on the shape vector. The radius of recognition sphere is minimum Euclidian distance, i.e. maximum similarity between the unknown model and each individual grammar created in the learning phase. By keeping information on derivations of individual syntactic elements, an alternative of parsing recognition is left. The analysis is very flexible, and permits the recognition of highly distorted or even partially visible objects. The output from syntactic analyzer is the measure of irregularity, and the method is thus applicable in any application where sample deformation is being examined.

  8. Sleep deprivation impairs spontaneous object-place but not novel-object recognition in rats.

    PubMed

    Ishikawa, Hiroko; Yamada, Kazuo; Pavlides, Constantine; Ichitani, Yukio

    2014-09-19

    Effects of sleep deprivation (SD) on one-trial recognition memory were investigated in rats using either a spontaneous novel-object or object-place recognition test. Rats were allowed to explore a field in which two identical objects were presented. After a delay period, they were placed again in the same field in which either: (1) one of the two objects was replaced by another object (novel-object recognition); or (2) one of the sample objects was moved to a different place (object-place recognition), and their exploration behavior to these objects was analyzed. Four hours SD immediately after the sample phase (early SD group) disrupted object-place recognition but not novel-object recognition, while SD 4-8h after the sample phase (delayed SD group) did not affect either paradigm. The results suggest that sleep selectively promotes the consolidation of hippocampal dependent memory, and that this effect is limited to within 4h after learning.

  9. Systemic L-Kynurenine sulfate administration disrupts object recognition memory, alters open field behavior and decreases c-Fos immunopositivity in C57Bl/6 mice.

    PubMed

    Varga, Dániel; Herédi, Judit; Kánvási, Zita; Ruszka, Marian; Kis, Zsolt; Ono, Etsuro; Iwamori, Naoki; Iwamori, Tokuko; Takakuwa, Hiroki; Vécsei, László; Toldi, József; Gellért, Levente

    2015-01-01

    L-Kynurenine (L-KYN) is a central metabolite of tryptophan degradation through the kynurenine pathway (KP). The systemic administration of L-KYN sulfate (L-KYNs) leads to a rapid elevation of the neuroactive KP metabolite kynurenic acid (KYNA). An elevated level of KYNA may have multiple effects on the synaptic transmission, resulting in complex behavioral changes, such as hypoactivity or spatial working memory deficits. These results emerged from studies that focused on rats, after low-dose L-KYNs treatment. However, in several studies neuroprotection was achieved through the administration of high-dose L-KYNs. In the present study, our aim was to investigate whether the systemic administration of a high dose of L-KYNs (300 mg/bwkg; i.p.) would produce alterations in behavioral tasks (open field or object recognition) in C57Bl/6j mice. To evaluate the changes in neuronal activity after L-KYNs treatment, in a separate group of animals we estimated c-Fos expression levels in the corresponding subcortical brain areas. The L-KYNs treatment did not affect the general ambulatory activity of C57Bl/6j mice, whereas it altered their moving patterns, elevating the movement velocity and resting time. Additionally, it seemed to increase anxiety-like behavior, as peripheral zone preference of the open field arena emerged and the rearing activity was attenuated. The treatment also completely abolished the formation of object recognition memory and resulted in decreases in the number of c-Fos-immunopositive-cells in the dorsal part of the striatum and in the CA1 pyramidal cell layer of the hippocampus. We conclude that a single exposure to L-KYNs leads to behavioral disturbances, which might be related to the altered basal c-Fos protein expression in C57Bl/6j mice.

  10. Systemic L-Kynurenine sulfate administration disrupts object recognition memory, alters open field behavior and decreases c-Fos immunopositivity in C57Bl/6 mice

    PubMed Central

    Varga, Dániel; Herédi, Judit; Kánvási, Zita; Ruszka, Marian; Kis, Zsolt; Ono, Etsuro; Iwamori, Naoki; Iwamori, Tokuko; Takakuwa, Hiroki; Vécsei, László; Toldi, József; Gellért, Levente

    2015-01-01

    L-Kynurenine (L-KYN) is a central metabolite of tryptophan degradation through the kynurenine pathway (KP). The systemic administration of L-KYN sulfate (L-KYNs) leads to a rapid elevation of the neuroactive KP metabolite kynurenic acid (KYNA). An elevated level of KYNA may have multiple effects on the synaptic transmission, resulting in complex behavioral changes, such as hypoactivity or spatial working memory deficits. These results emerged from studies that focused on rats, after low-dose L-KYNs treatment. However, in several studies neuroprotection was achieved through the administration of high-dose L-KYNs. In the present study, our aim was to investigate whether the systemic administration of a high dose of L-KYNs (300 mg/bwkg; i.p.) would produce alterations in behavioral tasks (open field or object recognition) in C57Bl/6j mice. To evaluate the changes in neuronal activity after L-KYNs treatment, in a separate group of animals we estimated c-Fos expression levels in the corresponding subcortical brain areas. The L-KYNs treatment did not affect the general ambulatory activity of C57Bl/6j mice, whereas it altered their moving patterns, elevating the movement velocity and resting time. Additionally, it seemed to increase anxiety-like behavior, as peripheral zone preference of the open field arena emerged and the rearing activity was attenuated. The treatment also completely abolished the formation of object recognition memory and resulted in decreases in the number of c-Fos-immunopositive-cells in the dorsal part of the striatum and in the CA1 pyramidal cell layer of the hippocampus. We conclude that a single exposure to L-KYNs leads to behavioral disturbances, which might be related to the altered basal c-Fos protein expression in C57Bl/6j mice. PMID:26136670

  11. Dissociating viewpoint costs in mental rotation and object recognition.

    PubMed

    Hayward, William G; Zhou, Guomei; Gauthier, Isabel; Harris, Irina M

    2006-10-01

    In a mental rotation task, participants must determine whether two stimuli match when one undergoes a rotation in 3-D space relative to the other. The key evidence for mental rotation is the finding of a linear increase in response times as objects are rotated farther apart. This signature increase in response times is also found in recognition of rotated objects, which has led many theorists to postulate mental rotation as a key transformational procedure in object recognition. We compared mental rotation and object recognition in tasks that used the same stimuli and presentation conditions and found that, whereas mental rotation costs increased relatively linearly with rotation, object recognition costs increased only over small rotations. Taken in conjunction with a recent brain imaging study, this dissociation in behavioral performance suggests that object recognition is based on matching of image features rather than on 3-D mental transformations.

  12. Visual Object Recognition and Tracking of Tools

    NASA Technical Reports Server (NTRS)

    English, James; Chang, Chu-Yin; Tardella, Neil

    2011-01-01

    A method has been created to automatically build an algorithm off-line, using computer-aided design (CAD) models, and to apply this at runtime. The object type is discriminated, and the position and orientation are identified. This system can work with a single image and can provide improved performance using multiple images provided from videos. The spatial processing unit uses three stages: (1) segmentation; (2) initial type, pose, and geometry (ITPG) estimation; and (3) refined type, pose, and geometry (RTPG) calculation. The image segmentation module files all the tools in an image and isolates them from the background. For this, the system uses edge-detection and thresholding to find the pixels that are part of a tool. After the pixels are identified, nearby pixels are grouped into blobs. These blobs represent the potential tools in the image and are the product of the segmentation algorithm. The second module uses matched filtering (or template matching). This approach is used for condensing synthetic images using an image subspace that captures key information. Three degrees of orientation, three degrees of position, and any number of degrees of freedom in geometry change are included. To do this, a template-matching framework is applied. This framework uses an off-line system for calculating template images, measurement images, and the measurements of the template images. These results are used online to match segmented tools against the templates. The final module is the RTPG processor. Its role is to find the exact states of the tools given initial conditions provided by the ITPG module. The requirement that the initial conditions exist allows this module to make use of a local search (whereas the ITPG module had global scope). To perform the local search, 3D model matching is used, where a synthetic image of the object is created and compared to the sensed data. The availability of low-cost PC graphics hardware allows rapid creation of synthetic images

  13. Object recognition may distort size perception.

    PubMed

    Wesp, R; Peckyno, A; McCall, S; Peters, S

    2000-06-01

    Size estimation may be influenced by characteristics recalled about the object viewed. This study evaluated the influence of object familiarity on estimation of size. We compared size estimates of several familiar objects with size estimates of undefined objects matched for dimensions of pattern and color. Those estimating the size of the familiar objects made significantly larger errors than those estimating the size of the undefined objects. In a second study size estimation errors from memory were larger than when objects were directly viewed. Experience with the objects appears to decrease accuracy of estimates of size but errors may be reduced by directly observing the object.

  14. Selective visual attention in object recognition and scene analysis

    NASA Astrophysics Data System (ADS)

    Gonzaga, Adilson; de Almeida Neves, Evelina M.; Frere, Annie F.

    1998-10-01

    An important feature of human vision system is the ability of selective visual attention. The stimulus that reaches the primate retina is processed in two different cortical pathways; one is specialized for object vision (`What') and the other for spatial vision (`Where'). By this, the visual system is able to recognize objects independently where they appear in the visual field. There are two major theories to explain the human visual attention. According to the Object- Based theory there is a limit on the isolated objects that could be perceived simultaneously and by the Space-Based theory there is a limit on the spatial areas from which the information could be taken up. This paper deals with the Object-Based theory that states the visual world occurs in two stages. The scene is segmented into isolated objects by region growing techniques in the pre-attentive stage. Invariant features (moments) are extracted and used as input of an Artificial Neural Network giving the probable object location (`Where'). In the focal-stage, particular objects are analyzed in detail through another neural network that performs the object recognition (`What'). The number of analyzed objects is based on a top-down process doing a consistent scene interpretation. With Visual Attention is possible the development of more efficient and flexible interfaces between low sensory information and high level process.

  15. Fast neuromimetic object recognition using FPGA outperforms GPU implementations.

    PubMed

    Orchard, Garrick; Martin, Jacob G; Vogelstein, R Jacob; Etienne-Cummings, Ralph

    2013-08-01

    Recognition of objects in still images has traditionally been regarded as a difficult computational problem. Although modern automated methods for visual object recognition have achieved steadily increasing recognition accuracy, even the most advanced computational vision approaches are unable to obtain performance equal to that of humans. This has led to the creation of many biologically inspired models of visual object recognition, among them the hierarchical model and X (HMAX) model. HMAX is traditionally known to achieve high accuracy in visual object recognition tasks at the expense of significant computational complexity. Increasing complexity, in turn, increases computation time, reducing the number of images that can be processed per unit time. In this paper we describe how the computationally intensive and biologically inspired HMAX model for visual object recognition can be modified for implementation on a commercial field-programmable aate Array, specifically the Xilinx Virtex 6 ML605 evaluation board with XC6VLX240T FPGA. We show that with minor modifications to the traditional HMAX model we can perform recognition on images of size 128 × 128 pixels at a rate of 190 images per second with a less than 1% loss in recognition accuracy in both binary and multiclass visual object recognition tasks.

  16. Automatic object recognition: critical issues and current approaches

    NASA Astrophysics Data System (ADS)

    Sadjadi, Firooz A.

    1991-08-01

    Automatic object recognition, with its diverse applications in numerous fields of science and technology, is permeating many aspects of military and civilian industries. This paper gives an overview of the issues confronting the automatic object recognition field and the approaches being used to address these issues.

  17. Object recognition and localization: the role of tactile sensors.

    PubMed

    Aggarwal, Achint; Kirchner, Frank

    2014-02-18

    Tactile sensors, because of their intrinsic insensitivity to lighting conditions and water turbidity, provide promising opportunities for augmenting the capabilities of vision sensors in applications involving object recognition and localization. This paper presents two approaches for haptic object recognition and localization for ground and underwater environments. The first approach called Batch Ransac and Iterative Closest Point augmented Particle Filter (BRICPPF) is based on an innovative combination of particle filters, Iterative-Closest-Point algorithm, and a feature-based Random Sampling and Consensus (RANSAC) algorithm for database matching. It can handle a large database of 3D-objects of complex shapes and performs a complete six-degree-of-freedom localization of static objects. The algorithms are validated by experimentation in ground and underwater environments using real hardware. To our knowledge this is the first instance of haptic object recognition and localization in underwater environments. The second approach is biologically inspired, and provides a close integration between exploration and recognition. An edge following exploration strategy is developed that receives feedback from the current state of recognition. A recognition by parts approach is developed which uses the BRICPPF for object sub-part recognition. Object exploration is either directed to explore a part until it is successfully recognized, or is directed towards new parts to endorse the current recognition belief. This approach is validated by simulation experiments.

  18. Object Recognition and Localization: The Role of Tactile Sensors

    PubMed Central

    Aggarwal, Achint; Kirchner, Frank

    2014-01-01

    Tactile sensors, because of their intrinsic insensitivity to lighting conditions and water turbidity, provide promising opportunities for augmenting the capabilities of vision sensors in applications involving object recognition and localization. This paper presents two approaches for haptic object recognition and localization for ground and underwater environments. The first approach called Batch Ransac and Iterative Closest Point augmented Particle Filter (BRICPPF) is based on an innovative combination of particle filters, Iterative-Closest-Point algorithm, and a feature-based Random Sampling and Consensus (RANSAC) algorithm for database matching. It can handle a large database of 3D-objects of complex shapes and performs a complete six-degree-of-freedom localization of static objects. The algorithms are validated by experimentation in ground and underwater environments using real hardware. To our knowledge this is the first instance of haptic object recognition and localization in underwater environments. The second approach is biologically inspired, and provides a close integration between exploration and recognition. An edge following exploration strategy is developed that receives feedback from the current state of recognition. A recognition by parts approach is developed which uses the BRICPPF for object sub-part recognition. Object exploration is either directed to explore a part until it is successfully recognized, or is directed towards new parts to endorse the current recognition belief. This approach is validated by simulation experiments. PMID:24553087

  19. An ERP Study on Self-Relevant Object Recognition

    ERIC Educational Resources Information Center

    Miyakoshi, Makoto; Nomura, Michio; Ohira, Hideki

    2007-01-01

    We performed an event-related potential study to investigate the self-relevance effect in object recognition. Three stimulus categories were prepared: SELF (participant's own objects), FAMILIAR (disposable and public objects, defined as objects with less-self-relevant familiarity), and UNFAMILIAR (others' objects). The participants' task was to…

  20. Contrast- and illumination-invariant object recognition from active sensation.

    PubMed

    Rentschler, Ingo; Osman, Erol; Jüttner, Martin

    2009-01-01

    It has been suggested that the deleterious effect of contrast reversal on visual recognition is unique to faces, not objects. Here we show from priming, supervised category learning, and generalization that there is no such thing as general invariance of recognition of non-face objects against contrast reversal and, likewise, changes in direction of illumination. However, when recognition varies with rendering conditions, invariance may be restored and effects of continuous learning may be reduced by providing prior object knowledge from active sensation. Our findings suggest that the degree of contrast invariance achieved reflects functional characteristics of object representations learned in a task-dependent fashion.

  1. Young Children's Self-Generated Object Views and Object Recognition

    ERIC Educational Resources Information Center

    James, Karin H.; Jones, Susan S.; Smith, Linda B.; Swain, Shelley N.

    2014-01-01

    Two important and related developments in children between 18 and 24 months of age are the rapid expansion of object name vocabularies and the emergence of an ability to recognize objects from sparse representations of their geometric shapes. In the same period, children also begin to show a preference for planar views (i.e., views of objects held…

  2. Infants' Recognition of Objects Using Canonical Color

    ERIC Educational Resources Information Center

    Kimura, Atsushi; Wada, Yuji; Yang, Jiale; Otsuka, Yumiko; Dan, Ippeita; Masuda, Tomohiro; Kanazawa, So; Yamaguchi, Masami K.

    2010-01-01

    We explored infants' ability to recognize the canonical colors of daily objects, including two color-specific objects (human face and fruit) and a non-color-specific object (flower), by using a preferential looking technique. A total of 58 infants between 5 and 8 months of age were tested with a stimulus composed of two color pictures of an object…

  3. Infants' Recognition of Objects Using Canonical Color

    ERIC Educational Resources Information Center

    Kimura, Atsushi; Wada, Yuji; Yang, Jiale; Otsuka, Yumiko; Dan, Ippeita; Masuda, Tomohiro; Kanazawa, So; Yamaguchi, Masami K.

    2010-01-01

    We explored infants' ability to recognize the canonical colors of daily objects, including two color-specific objects (human face and fruit) and a non-color-specific object (flower), by using a preferential looking technique. A total of 58 infants between 5 and 8 months of age were tested with a stimulus composed of two color pictures of an object…

  4. Mechanisms of object recognition: what we have learned from pigeons

    PubMed Central

    Soto, Fabian A.; Wasserman, Edward A.

    2014-01-01

    Behavioral studies of object recognition in pigeons have been conducted for 50 years, yielding a large body of data. Recent work has been directed toward synthesizing this evidence and understanding the visual, associative, and cognitive mechanisms that are involved. The outcome is that pigeons are likely to be the non-primate species for which the computational mechanisms of object recognition are best understood. Here, we review this research and suggest that a core set of mechanisms for object recognition might be present in all vertebrates, including pigeons and people, making pigeons an excellent candidate model to study the neural mechanisms of object recognition. Behavioral and computational evidence suggests that error-driven learning participates in object category learning by pigeons and people, and recent neuroscientific research suggests that the basal ganglia, which are homologous in these species, may implement error-driven learning of stimulus-response associations. Furthermore, learning of abstract category representations can be observed in pigeons and other vertebrates. Finally, there is evidence that feedforward visual processing, a central mechanism in models of object recognition in the primate ventral stream, plays a role in object recognition by pigeons. We also highlight differences between pigeons and people in object recognition abilities, and propose candidate adaptive specializations which may explain them, such as holistic face processing and rule-based category learning in primates. From a modern comparative perspective, such specializations are to be expected regardless of the model species under study. The fact that we have a good idea of which aspects of object recognition differ in people and pigeons should be seen as an advantage over other animal models. From this perspective, we suggest that there is much to learn about human object recognition from studying the “simple” brains of pigeons. PMID:25352784

  5. Mechanisms of object recognition: what we have learned from pigeons.

    PubMed

    Soto, Fabian A; Wasserman, Edward A

    2014-01-01

    Behavioral studies of object recognition in pigeons have been conducted for 50 years, yielding a large body of data. Recent work has been directed toward synthesizing this evidence and understanding the visual, associative, and cognitive mechanisms that are involved. The outcome is that pigeons are likely to be the non-primate species for which the computational mechanisms of object recognition are best understood. Here, we review this research and suggest that a core set of mechanisms for object recognition might be present in all vertebrates, including pigeons and people, making pigeons an excellent candidate model to study the neural mechanisms of object recognition. Behavioral and computational evidence suggests that error-driven learning participates in object category learning by pigeons and people, and recent neuroscientific research suggests that the basal ganglia, which are homologous in these species, may implement error-driven learning of stimulus-response associations. Furthermore, learning of abstract category representations can be observed in pigeons and other vertebrates. Finally, there is evidence that feedforward visual processing, a central mechanism in models of object recognition in the primate ventral stream, plays a role in object recognition by pigeons. We also highlight differences between pigeons and people in object recognition abilities, and propose candidate adaptive specializations which may explain them, such as holistic face processing and rule-based category learning in primates. From a modern comparative perspective, such specializations are to be expected regardless of the model species under study. The fact that we have a good idea of which aspects of object recognition differ in people and pigeons should be seen as an advantage over other animal models. From this perspective, we suggest that there is much to learn about human object recognition from studying the "simple" brains of pigeons.

  6. Eye movements during object recognition in visual agnosia.

    PubMed

    Charles Leek, E; Patterson, Candy; Paul, Matthew A; Rafal, Robert; Cristino, Filipe

    2012-07-01

    This paper reports the first ever detailed study about eye movement patterns during single object recognition in visual agnosia. Eye movements were recorded in a patient with an integrative agnosic deficit during two recognition tasks: common object naming and novel object recognition memory. The patient showed normal directional biases in saccades and fixation dwell times in both tasks and was as likely as controls to fixate within object bounding contour regardless of recognition accuracy. In contrast, following initial saccades of similar amplitude to controls, the patient showed a bias for short saccades. In object naming, but not in recognition memory, the similarity of the spatial distributions of patient and control fixations was modulated by recognition accuracy. The study provides new evidence about how eye movements can be used to elucidate the functional impairments underlying object recognition deficits. We argue that the results reflect a breakdown in normal functional processes involved in the integration of shape information across object structure during the visual perception of shape.

  7. Multiple-View Object Recognition in Smart Camera Networks

    NASA Astrophysics Data System (ADS)

    Yang, Allen Y.; Maji, Subhransu; Christoudias, C. Mario; Darrell, Trevor; Malik, Jitendra; Sastry, S. Shankar

    We study object recognition in low-power, low-bandwidth smart camera networks. The ability to perform robust object recognition is crucial for applications such as visual surveillance to track and identify objects of interest, and overcome visual nuisances such as occlusion and pose variations between multiple camera views. To accommodate limited bandwidth between the cameras and the base-station computer, the method utilizes the available computational power on the smart sensors to locally extract SIFT-type image features to represent individual camera views. We show that between a network of cameras, high-dimensional SIFT histograms exhibit a joint sparse pattern corresponding to a set of shared features in 3-D. Such joint sparse patterns can be explicitly exploited to encode the distributed signal via random projections. At the network station, multiple decoding schemes are studied to simultaneously recover the multiple-view object features based on a distributed compressive sensing theory. The system has been implemented on the Berkeley CITRIC smart camera platform. The efficacy of the algorithm is validated through extensive simulation and experiment.

  8. Real object use facilitates object recognition in semantic agnosia.

    PubMed

    Morady, Kamelia; Humphreys, Glyn W

    2009-01-01

    In the present paper we show that, in patients with poor semantic representations, the naming of real objects can improve when naming takes place after patients have been asked to use the objects, compared with when they name the objects either from vision or from touch alone, or together. In addition, the patients were strongly affected by action when required to name objects that were used correctly or incorrectly by the examiner. The data suggest that actions can be cued directly from sensory-motor associations, and that patients can then name on the basis of the evoked action.

  9. Object locating system

    DOEpatents

    Novak, James L.; Petterson, Ben

    1998-06-09

    A sensing system locates an object by sensing the object's effect on electric fields. The object's effect on the mutual capacitance of electrode pairs varies according to the distance between the object and the electrodes. A single electrode pair can sense the distance from the object to the electrodes. Multiple electrode pairs can more precisely locate the object in one or more dimensions.

  10. 'Breaking' position-invariant object recognition.

    PubMed

    Cox, David D; Meier, Philip; Oertelt, Nadja; DiCarlo, James J

    2005-09-01

    While it is often assumed that objects can be recognized irrespective of where they fall on the retina, little is known about the mechanisms underlying this ability. By exposing human subjects to an altered world where some objects systematically changed identity during the transient blindness that accompanies eye movements, we induced predictable object confusions across retinal positions, effectively 'breaking' position invariance. Thus, position invariance is not a rigid property of vision but is constantly adapting to the statistics of the environment.

  11. Recognition memory for object form and object location: an event-related potential study.

    PubMed

    Mecklinger, A; Meinshausen, R M

    1998-09-01

    In this study, the processes associated with retrieving object forms and object locations from working memory were examined with the use of simultaneously recorded event-related potential (ERP) activity. Subjects memorized object forms and their spatial locations and made either object-based or location-based recognition judgments. In Experiment 1, recognition performance was higher for object locations than for object forms. Old responses evoked more positive-going ERP activity between 0.3 and 1.8 sec poststimulus than did new responses. The topographic distribution of these old/new effects in the P300 time interval was task specific, with object-based recognition judgments being associated with anteriorly focused effects and location-based judgments with posteriorly focused effects. Late old/new effects were dominant at right frontal recordings. Using an interference paradigm, it was shown in Experiment 2 that visual representations were used to rehearse both object forms and object locations in working memory. The results of Experiment 3 indicated that the observed differential topographic distributions of the old/new effects in the P300 time interval are unlikely to reflect differences between easy and difficult recognition judgments. More specific effects were obtained for a subgroup of subjects for which the processing characteristics during location-based judgments presumably were similar to those in Experiment 1. These data, together with those from Experiment 1, indicate that different brain areas are engaged in retrieving object forms and object locations from working memory. Further analyses support the view that retrieval of object forms relies on conceptual semantic representation, whereas retrieving object locations is based on structural representations of spatial information. The effects in the later time intervals may play a functional role in post-retrieval processing, such as recollecting information from the study episode or other processes

  12. Category selectivity in human visual cortex: Beyond visual object recognition.

    PubMed

    Peelen, Marius V; Downing, Paul E

    2017-04-02

    Human ventral temporal cortex shows a categorical organization, with regions responding selectively to faces, bodies, tools, scenes, words, and other categories. Why is this? Traditional accounts explain category selectivity as arising within a hierarchical system dedicated to visual object recognition. For example, it has been proposed that category selectivity reflects the clustering of category-associated visual feature representations, or that it reflects category-specific computational algorithms needed to achieve view invariance. This visual object recognition framework has gained renewed interest with the success of deep neural network models trained to "recognize" objects: these hierarchical feed-forward networks show similarities to human visual cortex, including categorical separability. We argue that the object recognition framework is unlikely to fully account for category selectivity in visual cortex. Instead, we consider category selectivity in the context of other functions such as navigation, social cognition, tool use, and reading. Category-selective regions are activated during such tasks even in the absence of visual input and even in individuals with no prior visual experience. Further, they are engaged in close connections with broader domain-specific networks. Considering the diverse functions of these networks, category-selective regions likely encode their preferred stimuli in highly idiosyncratic formats; representations that are useful for navigation, social cognition, or reading are unlikely to be meaningfully similar to each other and to varying degrees may not be entirely visual. The demand for specific types of representations to support category-associated tasks may best account for category selectivity in visual cortex. This broader view invites new experimental and computational approaches. Copyright © 2017 Elsevier Ltd. All rights reserved.

  13. Object recognition of ladar with support vector machine

    NASA Astrophysics Data System (ADS)

    Sun, Jian-Feng; Li, Qi; Wang, Qi

    2005-01-01

    Intensity, range and Doppler images can be obtained by using laser radar. Laser radar can detect much more object information than other detecting sensor, such as passive infrared imaging and synthetic aperture radar (SAR), so it is well suited as the sensor of object recognition. Traditional method of laser radar object recognition is extracting target features, which can be influenced by noise. In this paper, a laser radar recognition method-Support Vector Machine is introduced. Support Vector Machine (SVM) is a new hotspot of recognition research after neural network. It has well performance on digital written and face recognition. Two series experiments about SVM designed for preprocessing and non-preprocessing samples are performed by real laser radar images, and the experiments results are compared.

  14. Object locating system

    DOEpatents

    Novak, J.L.; Petterson, B.

    1998-06-09

    A sensing system locates an object by sensing the object`s effect on electric fields. The object`s effect on the mutual capacitance of electrode pairs varies according to the distance between the object and the electrodes. A single electrode pair can sense the distance from the object to the electrodes. Multiple electrode pairs can more precisely locate the object in one or more dimensions. 12 figs.

  15. Category-Specificity in Visual Object Recognition

    ERIC Educational Resources Information Center

    Gerlach, Christian

    2009-01-01

    Are all categories of objects recognized in the same manner visually? Evidence from neuropsychology suggests they are not: some brain damaged patients are more impaired in recognizing natural objects than artefacts whereas others show the opposite impairment. Category-effects have also been demonstrated in neurologically intact subjects, but the…

  16. Category-Specificity in Visual Object Recognition

    ERIC Educational Resources Information Center

    Gerlach, Christian

    2009-01-01

    Are all categories of objects recognized in the same manner visually? Evidence from neuropsychology suggests they are not: some brain damaged patients are more impaired in recognizing natural objects than artefacts whereas others show the opposite impairment. Category-effects have also been demonstrated in neurologically intact subjects, but the…

  17. 3D object recognition in TOF data sets

    NASA Astrophysics Data System (ADS)

    Hess, Holger; Albrecht, Martin; Grothof, Markus; Hussmann, Stephan; Oikonomidis, Nikolaos; Schwarte, Rudolf

    2003-08-01

    In the last years 3D-Vision systems based on the Time-Of-Flight (TOF) principle have gained more importance than Stereo Vision (SV). TOF offers a direct depth-data acquisition, whereas SV involves a great amount of computational power for a comparable 3D data set. Due to the enormous progress in TOF-techniques, nowadays 3D cameras can be manufactured and be used for many practical applications. Hence there is a great demand for new accurate algorithms for 3D object recognition and classification. This paper presents a new strategy and algorithm designed for a fast and solid object classification. A challenging example - accurate classification of a (half-) sphere - demonstrates the performance of the developed algorithm. Finally, the transition from a general model of the system to specific applications such as Intelligent Airbag Control and Robot Assistance in Surgery are introduced. The paper concludes with the current research results in the above mentioned fields.

  18. The subjective experience of object recognition: comparing metacognition for object detection and object categorization.

    PubMed

    Meuwese, Julia D I; van Loon, Anouk M; Lamme, Victor A F; Fahrenfort, Johannes J

    2014-05-01

    Perceptual decisions seem to be made automatically and almost instantly. Constructing a unitary subjective conscious experience takes more time. For example, when trying to avoid a collision with a car on a foggy road you brake or steer away in a reflex, before realizing you were in a near accident. This subjective aspect of object recognition has been given little attention. We used metacognition (assessed with confidence ratings) to measure subjective experience during object detection and object categorization for degraded and masked objects, while objective performance was matched. Metacognition was equal for degraded and masked objects, but categorization led to higher metacognition than did detection. This effect turned out to be driven by a difference in metacognition for correct rejection trials, which seemed to be caused by an asymmetry of the distractor stimulus: It does not contain object-related information in the detection task, whereas it does contain such information in the categorization task. Strikingly, this asymmetry selectively impacted metacognitive ability when objective performance was matched. This finding reveals a fundamental difference in how humans reflect versus act on information: When matching the amount of information required to perform two tasks at some objective level of accuracy (acting), metacognitive ability (reflecting) is still better in tasks that rely on positive evidence (categorization) than in tasks that rely more strongly on an absence of evidence (detection).

  19. A Taxonomy of 3D Occluded Objects Recognition Techniques

    NASA Astrophysics Data System (ADS)

    Soleimanizadeh, Shiva; Mohamad, Dzulkifli; Saba, Tanzila; Al-ghamdi, Jarallah Saleh

    2016-03-01

    The overall performances of object recognition techniques under different condition (e.g., occlusion, viewpoint, and illumination) have been improved significantly in recent years. New applications and hardware are shifted towards digital photography, and digital media. This faces an increase in Internet usage requiring object recognition for certain applications; particularly occulded objects. However occlusion is still an issue unhandled, interlacing the relations between extracted feature points through image, research is going on to develop efficient techniques and easy to use algorithms that would help users to source images; this need to overcome problems and issues regarding occlusion. The aim of this research is to review recognition occluded objects algorithms and figure out their pros and cons to solve the occlusion problem features, which are extracted from occluded object to distinguish objects from other co-existing objects by determining the new techniques, which could differentiate the occluded fragment and sections inside an image.

  20. Visuo-haptic multisensory object recognition, categorization, and representation

    PubMed Central

    Lacey, Simon; Sathian, K.

    2014-01-01

    Visual and haptic unisensory object processing show many similarities in terms of categorization, recognition, and representation. In this review, we discuss how these similarities contribute to multisensory object processing. In particular, we show that similar unisensory visual and haptic representations lead to a shared multisensory representation underlying both cross-modal object recognition and view-independence. This shared representation suggests a common neural substrate and we review several candidate brain regions, previously thought to be specialized for aspects of visual processing, that are now known also to be involved in analogous haptic tasks. Finally, we lay out the evidence for a model of multisensory object recognition in which top-down and bottom-up pathways to the object-selective lateral occipital complex are modulated by object familiarity and individual differences in object and spatial imagery. PMID:25101014

  1. Pattern recognition of multiple objects using adaptive correlation filters

    NASA Astrophysics Data System (ADS)

    Pinedo-García, Marco I.; Kober, Vitaly

    2007-09-01

    A new method for reliable pattern recognition of multiple distorted objects in a cluttered background and consequent classification of the detected objects is proposed. The method is based on a bank of composite correlation filters. The filters are designed with the help of an iterative algorithm exploiting a modified version of synthetic discriminant functions. The bank consists of a minimal quantity of the filters required for a given input scene to guarantee a prespecified value of discrimination capability for pattern recognition and classification of all objects. Statistical analysis of the number of required correlations versus the recognition performance is provided and discussed. Computer simulation results obtained with the proposed method are compared with those of known techniques in terms of performance criteria for recognition and classification of objects.

  2. Orientation-invariant object recognition: evidence from repetition blindness.

    PubMed

    Harris, Irina M; Dux, Paul E

    2005-02-01

    The question of whether object recognition is orientation-invariant or orientation-dependent was investigated using a repetition blindness (RB) paradigm. In RB, the second occurrence of a repeated stimulus is less likely to be reported, compared to the occurrence of a different stimulus, if it occurs within a short time of the first presentation. This failure is usually interpreted as a difficulty in assigning two separate episodic tokens to the same visual type. Thus, RB can provide useful information about which representations are treated as the same by the visual system. Two experiments tested whether RB occurs for repeated objects that were either in identical orientations, or differed by 30, 60, 90, or 180 degrees . Significant RB was found for all orientation differences, consistent with the existence of orientation-invariant object representations. However, under some circumstances, RB was reduced or even eliminated when the repeated object was rotated by 180 degrees , suggesting easier individuation of the repeated objects in this case. A third experiment confirmed that the upside-down orientation is processed more easily than other rotated orientations. The results indicate that, although object identity can be determined independently of orientation, orientation plays an important role in establishing distinct episodic representations of a repeated object, thus enabling one to report them as separate events.

  3. Determinants of novel object and location recognition during development.

    PubMed

    Jablonski, S A; Schreiber, W B; Westbrook, S R; Brennan, L E; Stanton, M E

    2013-11-01

    In the novel object recognition (OR) paradigm, rats are placed in an arena where they encounter two sample objects during a familiarization phase. A few minutes later, they are returned to the same arena and are presented with a familiar object and a novel object. The object location recognition (OL) variant involves the same familiarization procedure but during testing one of the familiar objects is placed in a novel location. Normal adult rats are able to perform both the OR and OL tasks, as indicated by enhanced exploration of the novel vs. the familiar test item. Rats with hippocampal lesions perform the OR but not OL task indicating a role of spatial memory in OL. Recently, these tasks have been used to study the ontogeny of spatial memory but the literature has yielded conflicting results. The current experiments add to this literature by: (1) behaviorally characterizing these paradigms in postnatal day (PD) 21, 26 and 31-day-old rats; (2) examining the role of NMDA systems in OR vs. OL; and (3) investigating the effects of neonatal alcohol exposure on both tasks. Results indicate that normal-developing rats are able to perform OR and OL by PD21, with greater novelty exploration in the OR task at each age. Second, memory acquisition in the OL but not OR task requires NMDA receptor function in juvenile rats [corrected]. Lastly, neonatal alcohol exposure does not disrupt performance in either task. Implications for the ontogeny of incidental spatial learning and its disruption by developmental alcohol exposure are discussed.

  4. Leveraging Cognitive Context for Object Recognition

    DTIC Science & Technology

    2014-06-01

    looking at a desk so I may see my computer next), as well as internal (e.g., I was told to look for a banana so I may be likely to see one soon). We...itself); raisins and banana are tied for the second-most likely object to be seen next. When raisins are seen, context again suggests that raisins are...most likely to be seen next, with banana the second- most likely to be seen next. This pattern repeats itself for the second set of objects

  5. Crowding: a cortical constraint on object recognition.

    PubMed

    Pelli, Denis G

    2008-08-01

    The external world is mapped retinotopically onto the primary visual cortex (V1). We show here that objects in the world, unless they are very dissimilar, can be recognized only if they are sufficiently separated in visual cortex: specifically, in V1, at least 6mm apart in the radial direction (increasing eccentricity) or 1mm apart in the circumferential direction (equal eccentricity). Objects closer together than this critical spacing are perceived as an unidentifiable jumble. This is called 'crowding'. It severely limits visual processing, including speed of reading and searching. The conclusion about visual cortex rests on three findings. First, psychophysically, the necessary 'critical' spacing, in the visual field, is proportional to (roughly half) the eccentricity of the objects. Second, the critical spacing is independent of the size and kind of object. Third, anatomically, the representation of the visual field on the cortical surface is such that the position in V1 (and several other areas) is the logarithm of eccentricity in the visual field. Furthermore, we show that much of this can be accounted for by supposing that each 'combining field', defined by the critical spacing measurements, is implemented by a fixed number of cortical neurons.

  6. Object Recognition and Random Image Structure Evolution

    ERIC Educational Resources Information Center

    Sadr, Jvid; Sinha, Pawan

    2004-01-01

    We present a technique called Random Image Structure Evolution (RISE) for use in experimental investigations of high-level visual perception. Potential applications of RISE include the quantitative measurement of perceptual hysteresis and priming, the study of the neural substrates of object perception, and the assessment and detection of subtle…

  7. Object Recognition and Random Image Structure Evolution

    ERIC Educational Resources Information Center

    Sadr, Jvid; Sinha, Pawan

    2004-01-01

    We present a technique called Random Image Structure Evolution (RISE) for use in experimental investigations of high-level visual perception. Potential applications of RISE include the quantitative measurement of perceptual hysteresis and priming, the study of the neural substrates of object perception, and the assessment and detection of subtle…

  8. Comparing object recognition from binary and bipolar edge features

    PubMed Central

    Jung, Jae-Hyun; Pu, Tian; Peli, Eli

    2017-01-01

    Edges derived from abrupt luminance changes in images carry essential information for object recognition. Typical binary edge images (black edges on white background or white edges on black background) have been used to represent features (edges and cusps) in scenes. However, the polarity of cusps and edges may contain important depth information (depth from shading) which is lost in the binary edge representation. This depth information may be restored, to some degree, using bipolar edges. We compared recognition rates of 16 binary edge images, or bipolar features, by 26 subjects. Object recognition rates were higher with bipolar edges and the improvement was significant in scenes with complex backgrounds.

  9. Changes in functional connectivity support conscious object recognition.

    PubMed

    Imamoglu, Fatma; Kahnt, Thorsten; Koch, Christof; Haynes, John-Dylan

    2012-12-01

    What are the brain mechanisms that mediate conscious object recognition? To investigate this question, it is essential to distinguish between brain processes that cause conscious recognition of a stimulus from other correlates of its sensory processing. Previous fMRI studies have identified large-scale brain activity ranging from striate to high-level sensory and prefrontal regions associated with conscious visual perception or recognition. However, the possible role of changes in connectivity during conscious perception between these regions has only rarely been studied. Here, we used fMRI and connectivity analyses, together with 120 custom-generated, two-tone, Mooney images to directly assess whether conscious recognition of an object is accompanied by a dynamical change in the functional coupling between extrastriate cortex and prefrontal areas. We compared recognizing an object versus not recognizing it in 19 naïve subjects using two different response modalities. We find that connectivity between the extrastriate cortex and the dorsolateral prefrontal cortex (DLPFC) increases when objects are consciously recognized. This interaction was independent of the response modality used to report conscious recognition. Furthermore, computing the difference in Granger causality between recognized and not recognized conditions reveals stronger feedforward connectivity than feedback connectivity when subjects recognized the objects. We suggest that frontal and visual brain regions are part of a functional network that supports conscious object recognition by changes in functional connectivity.

  10. Enriched environment effects on remote object recognition memory.

    PubMed

    Melani, Riccardo; Chelini, Gabriele; Cenni, Maria Cristina; Berardi, Nicoletta

    2017-04-12

    Since Ebbinghaus' classical work on oblivion and saving effects, we know that declarative memories may become at first spontaneously irretrievable and only subsequently completely extinguished. Recently, this time-dependent path towards memory-trace loss has been shown to correlate with different patterns of brain activation. Environmental enrichment (EE) enhances learning and memory and affects system memory consolidation. However, there is no evidence on whether and how EE could affect the time-dependent path towards oblivion. We used Object Recognition Test (ORT) to assess in adult mice put in EE for 40 days (EE mice) or left in standard condition (SC mice) memory retrieval of the familiar objects 9 and 21 days after learning with or without a brief retraining performed the day before. We found that SC mice show preferential exploration of new object at day 9 only with retraining, while EE mice do it even without. At day 21 SC mice do not show preferential exploration of novel object, irrespective of the retraining, while EE mice are still capable to benefit from retraining, even if they were not able to spontaneously recover the trace. Analysis of c-fos expression 20 days after learning shows a different pattern of active brain areas in response to the retraining session in EE and SC mice, with SC mice recruiting the same brain network as naïve SC or EE mice following de novo learning. This suggests that EE promotes formation of longer-lasting object recognition memory, allowing a longer time window during which saving is present.

  11. Object similarity affects the perceptual strategy underlying invariant visual object recognition in rats

    PubMed Central

    Rosselli, Federica B.; Alemi, Alireza; Ansuini, Alessio; Zoccolan, Davide

    2015-01-01

    In recent years, a number of studies have explored the possible use of rats as models of high-level visual functions. One central question at the root of such an investigation is to understand whether rat object vision relies on the processing of visual shape features or, rather, on lower-order image properties (e.g., overall brightness). In a recent study, we have shown that rats are capable of extracting multiple features of an object that are diagnostic of its identity, at least when those features are, structure-wise, distinct enough to be parsed by the rat visual system. In the present study, we have assessed the impact of object structure on rat perceptual strategy. We trained rats to discriminate between two structurally similar objects, and compared their recognition strategies with those reported in our previous study. We found that, under conditions of lower stimulus discriminability, rat visual discrimination strategy becomes more view-dependent and subject-dependent. Rats were still able to recognize the target objects, in a way that was largely tolerant (i.e., invariant) to object transformation; however, the larger structural and pixel-wise similarity affected the way objects were processed. Compared to the findings of our previous study, the patterns of diagnostic features were: (i) smaller and more scattered; (ii) only partially preserved across object views; and (iii) only partially reproducible across rats. On the other hand, rats were still found to adopt a multi-featural processing strategy and to make use of part of the optimal discriminatory information afforded by the two objects. Our findings suggest that, as in humans, rat invariant recognition can flexibly rely on either view-invariant representations of distinctive object features or view-specific object representations, acquired through learning. PMID:25814936

  12. Object similarity affects the perceptual strategy underlying invariant visual object recognition in rats.

    PubMed

    Rosselli, Federica B; Alemi, Alireza; Ansuini, Alessio; Zoccolan, Davide

    2015-01-01

    In recent years, a number of studies have explored the possible use of rats as models of high-level visual functions. One central question at the root of such an investigation is to understand whether rat object vision relies on the processing of visual shape features or, rather, on lower-order image properties (e.g., overall brightness). In a recent study, we have shown that rats are capable of extracting multiple features of an object that are diagnostic of its identity, at least when those features are, structure-wise, distinct enough to be parsed by the rat visual system. In the present study, we have assessed the impact of object structure on rat perceptual strategy. We trained rats to discriminate between two structurally similar objects, and compared their recognition strategies with those reported in our previous study. We found that, under conditions of lower stimulus discriminability, rat visual discrimination strategy becomes more view-dependent and subject-dependent. Rats were still able to recognize the target objects, in a way that was largely tolerant (i.e., invariant) to object transformation; however, the larger structural and pixel-wise similarity affected the way objects were processed. Compared to the findings of our previous study, the patterns of diagnostic features were: (i) smaller and more scattered; (ii) only partially preserved across object views; and (iii) only partially reproducible across rats. On the other hand, rats were still found to adopt a multi-featural processing strategy and to make use of part of the optimal discriminatory information afforded by the two objects. Our findings suggest that, as in humans, rat invariant recognition can flexibly rely on either view-invariant representations of distinctive object features or view-specific object representations, acquired through learning.

  13. Multiple Kernel Learning for Visual Object Recognition: A Review.

    PubMed

    Bucak, Serhat S; Rong Jin; Jain, Anil K

    2014-07-01

    Multiple kernel learning (MKL) is a principled approach for selecting and combining kernels for a given recognition task. A number of studies have shown that MKL is a useful tool for object recognition, where each image is represented by multiple sets of features and MKL is applied to combine different feature sets. We review the state-of-the-art for MKL, including different formulations and algorithms for solving the related optimization problems, with the focus on their applications to object recognition. One dilemma faced by practitioners interested in using MKL for object recognition is that different studies often provide conflicting results about the effectiveness and efficiency of MKL. To resolve this, we conduct extensive experiments on standard datasets to evaluate various approaches to MKL for object recognition. We argue that the seemingly contradictory conclusions offered by studies are due to different experimental setups. The conclusions of our study are: (i) given a sufficient number of training examples and feature/kernel types, MKL is more effective for object recognition than simple kernel combination (e.g., choosing the best performing kernel or average of kernels); and (ii) among the various approaches proposed for MKL, the sequential minimal optimization, semi-infinite programming, and level method based ones are computationally most efficient.

  14. Induced gamma band responses predict recognition delays during object identification.

    PubMed

    Martinovic, Jasna; Gruber, Thomas; Müller, Matthias M

    2007-06-01

    Neural mechanisms of object recognition seem to rely on activity of distributed neural assemblies coordinated by synchronous firing in the gamma-band range (>20 Hz). In the present electroencephalogram (EEG) study, we investigated induced gamma band activity during the naming of line drawings of upright objects and objects rotated in the image plane. Such plane-rotation paradigms elicit view-dependent processing, leading to delays in recognition of disoriented objects. Our behavioral results showed reaction time delays for rotated, as opposed to upright, images. These delays were accompanied by delays in the peak latency of induced gamma band responses (GBRs), in the absence of any effects on other measures of EEG activity. The latency of the induced GBRs has thus, for the first time, been selectively modulated by an experimental manipulation that delayed recognition. This finding indicates that induced GBRs have a genuine role as neural markers of late representational processes during object recognition. In concordance with the view that object recognition is achieved through dynamic learning processes, we propose that induced gamma band activity could be one of the possible cortical markers of such dynamic object coding.

  15. Distortion-tolerant 3-D object recognition by using single exposure on-axis digital holography.

    PubMed

    Kim, Daesuk; Javidi, Bahram

    2004-11-01

    We present a distortion-tolerant 3-D object recognition system using single exposure on-axis digital holography. In contrast to distortion-tolerant 3-D object recognition employing conventional phase shifting scheme which requires multiple exposures, our proposed method requires only one single digital hologram to be synthesized and used for distortion-tolerant 3-D object recognition. A benefit of the single exposure based on-axis approach is enhanced practicality of digital holography for distortion-tolerant 3-D object recognition in terms of its simplicity and high tolerance to external scene parameters such as moving targets. This paper shows experimentally, that single exposure on-axis digital holography is capable of providing a distortion-tolerant 3-D object recognition capability.

  16. Robust object recognition under partial occlusions using NMF.

    PubMed

    Soukup, Daniel; Bajla, Ivan

    2008-01-01

    In recent years, nonnegative matrix factorization (NMF) methods of a reduced image data representation attracted the attention of computer vision community. These methods are considered as a convenient part-based representation of image data for recognition tasks with occluded objects. A novel modification in NMF recognition tasks is proposed which utilizes the matrix sparseness control introduced by Hoyer. We have analyzed the influence of sparseness on recognition rates (RRs) for various dimensions of subspaces generated for two image databases, ORL face database, and USPS handwritten digit database. We have studied the behavior of four types of distances between a projected unknown image object and feature vectors in NMF subspaces generated for training data. One of these metrics also is a novelty we proposed. In the recognition phase, partial occlusions in the test images have been modeled by putting two randomly large, randomly positioned black rectangles into each test image.

  17. Invariance in Visual Object Recognition Requires Training: A Computational Argument

    PubMed Central

    Goris, Robbe L. T.; de Beeck, Hans P. Op

    2009-01-01

    Visual object recognition is remarkably accurate and robust, yet its neurophysiological underpinnings are poorly understood. Single cells in brain regions thought to underlie object recognition code for many stimulus aspects, which poses a limit on their invariance. Combining the responses of multiple non-invariant neurons via weighted linear summation offers an optimal decoding strategy, which may be able to achieve invariant object recognition. However, because object identification is essentially parameter optimization in this model, the characteristics of the identification task trained to perform are critically important. If this task does not require invariance, a neural population-code is inherently more selective but less tolerant than the single-neurons constituting the population. Nevertheless, tolerance can be learned – provided that it is trained for – at the cost of selectivity. We argue that this model is an interesting null-hypothesis to compare behavioral results with and conclude that it may explain several experimental findings. PMID:20589239

  18. A hippocampal signature of perceptual learning in object recognition.

    PubMed

    Guggenmos, Matthias; Rothkirch, Marcus; Obermayer, Klaus; Haynes, John-Dylan; Sterzer, Philipp

    2015-04-01

    Perceptual learning is the improvement in perceptual performance through training or exposure. Here, we used fMRI before and after extensive behavioral training to investigate the effects of perceptual learning on the recognition of objects under challenging viewing conditions. Objects belonged either to trained or untrained categories. Trained categories were further subdivided into trained and untrained exemplars and were coupled with high or low monetary rewards during training. After a 3-day training, object recognition was markedly improved. Although there was a considerable transfer of learning to untrained exemplars within categories, an enhancing effect of reward reinforcement was specific to trained exemplars. fMRI showed that hippocampus responses to both trained and untrained exemplars of trained categories were enhanced by perceptual learning and correlated with the effect of reward reinforcement. Our results suggest a key role of hippocampus in object recognition after perceptual learning.

  19. Innate visual object recognition in vertebrates: some proposed pathways and mechanisms.

    PubMed

    Sewards, Terence V; Sewards, Mark A

    2002-08-01

    Almost all vertebrates are capable of recognizing biologically relevant stimuli at or shortly after birth, and in some phylogenetically ancient species visual object recognition is exclusively innate. Extensive and detailed studies of the anuran visual system have resulted in the determination of the neural structures and pathways involved in innate prey and predator recognition in these species [Behav. Brain Sci. 10 (1987) 337; Comp. Biochem. Physiol. A 128 (2001) 417]. The structures involved include the optic tectum, pretectal nuclei and an area within the mesencephalic tegmentum. Here we investigate the structures and pathways involved in innate stimulus recognition in avian, rodent and primate species. We discuss innate stimulus preferences in maternal imprinting in chicks and argue that these preferences are due to innate visual recognition of conspecifics, entirely mediated by subtelencephalic structures. In rodent species, brainstem structures largely homologous to the components of the anuran subcortical visual system mediate innate visual object recognition. The primary components of the mammalian subcortical visual system are the superior colliculus, nucleus of the optic tract, anterior and posterior pretectal nuclei, nucleus of the posterior commissure, and an area within the mesopontine reticular formation that includes parts of the cuneiform, subcuneiform and pedunculopontine nuclei. We argue that in rodent species the innate sensory recognition systems function throughout ontogeny, acting in parallel with cortical sensory and recognition systems. In primates the structures involved in innate stimulus recognition are essentially the same as those in rodents, but overt innate recognition is only present in very early ontogeny, and after a transition period gives way to learned object recognition mediated by cortical structures. After the transition period, primate subcortical sensory systems still function to provide implicit innate stimulus

  20. The Neural Regions Sustaining Episodic Encoding and Recognition of Objects

    ERIC Educational Resources Information Center

    Hofer, Alex; Siedentopf, Christian M.; Ischebeck, Anja; Rettenbacher, Maria A.; Widschwendter, Christian G.; Verius, Michael; Golaszewski, Stefan M.; Koppelstaetter, Florian; Felber, Stephan; Wolfgang Fleischhacker, W.

    2007-01-01

    In this functional MRI experiment, encoding of objects was associated with activation in left ventrolateral prefrontal/insular and right dorsolateral prefrontal and fusiform regions as well as in the left putamen. By contrast, correct recognition of previously learned objects (R judgments) produced activation in left superior frontal, bilateral…

  1. Spontaneous Object Recognition Memory in Aged Rats: Complexity versus Similarity

    ERIC Educational Resources Information Center

    Gamiz, Fernando; Gallo, Milagros

    2012-01-01

    Previous work on the effect of aging on spontaneous object recognition (SOR) memory tasks in rats has yielded controversial results. Although the results at long-retention intervals are consistent, conflicting results have been reported at shorter delays. We have assessed the potential relevance of the type of object used in the performance of…

  2. The Neural Regions Sustaining Episodic Encoding and Recognition of Objects

    ERIC Educational Resources Information Center

    Hofer, Alex; Siedentopf, Christian M.; Ischebeck, Anja; Rettenbacher, Maria A.; Widschwendter, Christian G.; Verius, Michael; Golaszewski, Stefan M.; Koppelstaetter, Florian; Felber, Stephan; Wolfgang Fleischhacker, W.

    2007-01-01

    In this functional MRI experiment, encoding of objects was associated with activation in left ventrolateral prefrontal/insular and right dorsolateral prefrontal and fusiform regions as well as in the left putamen. By contrast, correct recognition of previously learned objects (R judgments) produced activation in left superior frontal, bilateral…

  3. Spontaneous Object Recognition Memory in Aged Rats: Complexity versus Similarity

    ERIC Educational Resources Information Center

    Gamiz, Fernando; Gallo, Milagros

    2012-01-01

    Previous work on the effect of aging on spontaneous object recognition (SOR) memory tasks in rats has yielded controversial results. Although the results at long-retention intervals are consistent, conflicting results have been reported at shorter delays. We have assessed the potential relevance of the type of object used in the performance of…

  4. Pattern recognition systems and procedures

    NASA Technical Reports Server (NTRS)

    Nelson, G. D.; Serreyn, D. V.

    1972-01-01

    The objectives of the pattern recognition tasks are to develop (1) a man-machine interactive data processing system; and (2) procedures to determine effective features as a function of time for crops and soils. The signal analysis and dissemination equipment, SADE, is being developed as a man-machine interactive data processing system. SADE will provide imagery and multi-channel analog tape inputs for digitation and a color display of the data. SADE is an essential tool to aid in the investigation to determine useful features as a function of time for crops and soils. Four related studies are: (1) reliability of the multivariate Gaussian assumption; (2) usefulness of transforming features with regard to the classifier probability of error; (3) advantage of selecting quantizer parameters to minimize the classifier probability of error; and (4) advantage of using contextual data. The study of transformation of variables (features), especially those experimental studies which can be completed with the SADE system, will be done.

  5. Picture object recognition in an American black bear (Ursus americanus).

    PubMed

    Johnson-Ulrich, Zoe; Vonk, Jennifer; Humbyrd, Mary; Crowley, Marilyn; Wojtkowski, Ela; Yates, Florence; Allard, Stephanie

    2016-11-01

    Many animals have been tested for conceptual discriminations using two-dimensional images as stimuli, and many of these species appear to transfer knowledge from 2D images to analogous real life objects. We tested an American black bear for picture-object recognition using a two alternative forced choice task. She was presented with four unique sets of objects and corresponding pictures. The bear showed generalization from both objects to pictures and pictures to objects; however, her transfer was superior when transferring from real objects to pictures, suggesting that bears can recognize visual features from real objects within photographic images during discriminations.

  6. Object Recognition with Severe Spatial Deficits in Williams Syndrome: Sparing and Breakdown

    ERIC Educational Resources Information Center

    Landau, Barbara; Hoffman, James E.; Kurz, Nicole

    2006-01-01

    Williams syndrome (WS) is a rare genetic disorder that results in severe visual-spatial cognitive deficits coupled with relative sparing in language, face recognition, and certain aspects of motion processing. Here, we look for evidence for sparing or impairment in another cognitive system--object recognition. Children with WS, normal mental-age…

  7. Object Recognition with Severe Spatial Deficits in Williams Syndrome: Sparing and Breakdown

    ERIC Educational Resources Information Center

    Landau, Barbara; Hoffman, James E.; Kurz, Nicole

    2006-01-01

    Williams syndrome (WS) is a rare genetic disorder that results in severe visual-spatial cognitive deficits coupled with relative sparing in language, face recognition, and certain aspects of motion processing. Here, we look for evidence for sparing or impairment in another cognitive system--object recognition. Children with WS, normal mental-age…

  8. Distinct patterns of viewpoint-dependent BOLD activity during common-object recognition and mental rotation.

    PubMed

    Wilson, Kevin D; Farah, Martha J

    2006-01-01

    A fundamental but unanswered question about the human visual system concerns the way in which misoriented objects are recognized. One hypothesis maintains that representations of incoming stimuli are transformed via parietally based spatial normalization mechanisms (eg mental rotation) to match view-specific representations in long-term memory. Using fMRI, we tested this hypothesis by directly comparing patterns of brain activity evoked during classic mental rotation and misoriented object recognition involving everyday objects. BOLD activity increased systematically with stimulus rotation within the ventral visual stream during object recognition and within the dorsal visual stream during mental rotation. More specifically, viewpoint-dependent activity was significantly greater in the right superior parietal lobule during mental rotation than during object recognition. In contrast, viewpoint-dependent activity was significantly greater in the right fusiform gyrus during object recognition than during mental rotation. In addition to these differences in viewpoint-dependent activity, object recognition and mental rotation produced distinct patterns of brain activity, independent of stimulus rotation: object recognition resulted in greater overall activity within ventral stream visual areas and mental rotation resulted in greater overall activity within dorsal stream visual areas. The present results are inconsistent with the hypothesis that misoriented object recognition is mediated by structures within the parietal lobe that are known to be involved in mental rotation.

  9. Three-dimensional-object recognition by use of single-exposure on-axis digital holography.

    PubMed

    Javidi, Bahram; Kim, Daesuk

    2005-02-01

    On-axis phase-shifting digital holography requires recording of multiple holograms. We describe a novel real-time three-dimensional- (3-D-) object recognition system that uses single-exposure on-axis digital holography. In contrast to 3-D-object recognition by means of a conventional phase-shifting scheme that requires multiple exposures, our proposed method requires only a single digital hologram to be synthesized and used to recognize 3-D objects. A benefit of the proposed 3-D recognition method is enhanced practicality of digital holography for 3-D recognition in terms of its simplicity and greater robustness to external scene parameters such as moving targets and environmental noise factors. We show experimentally the utility of the single-exposure on-axis digital holography-based 3-D-object recognition method.

  10. Object recognition and pose estimation of planar objects from range data

    NASA Technical Reports Server (NTRS)

    Pendleton, Thomas W.; Chien, Chiun Hong; Littlefield, Mark L.; Magee, Michael

    1994-01-01

    The Extravehicular Activity Helper/Retriever (EVAHR) is a robotic device currently under development at the NASA Johnson Space Center that is designed to fetch objects or to assist in retrieving an astronaut who may have become inadvertently de-tethered. The EVAHR will be required to exhibit a high degree of intelligent autonomous operation and will base much of its reasoning upon information obtained from one or more three-dimensional sensors that it will carry and control. At the highest level of visual cognition and reasoning, the EVAHR will be required to detect objects, recognize them, and estimate their spatial orientation and location. The recognition phase and estimation of spatial pose will depend on the ability of the vision system to reliably extract geometric features of the objects such as whether the surface topologies observed are planar or curved and the spatial relationships between the component surfaces. In order to achieve these tasks, three-dimensional sensing of the operational environment and objects in the environment will therefore be essential. One of the sensors being considered to provide image data for object recognition and pose estimation is a phase-shift laser scanner. The characteristics of the data provided by this scanner have been studied and algorithms have been developed for segmenting range images into planar surfaces, extracting basic features such as surface area, and recognizing the object based on the characteristics of extracted features. Also, an approach has been developed for estimating the spatial orientation and location of the recognized object based on orientations of extracted planes and their intersection points. This paper presents some of the algorithms that have been developed for the purpose of recognizing and estimating the pose of objects as viewed by the laser scanner, and characterizes the desirability and utility of these algorithms within the context of the scanner itself, considering data quality and

  11. Improving human object recognition performance using video enhancement techniques

    NASA Astrophysics Data System (ADS)

    Whitman, Lucy S.; Lewis, Colin; Oakley, John P.

    2004-12-01

    Atmospheric scattering causes significant degradation in the quality of video images, particularly when imaging over long distances. The principle problem is the reduction in contrast due to scattered light. It is known that when the scattering particles are not too large compared with the imaging wavelength (i.e. Mie scattering) then high spatial resolution information may be contained within a low-contrast image. Unfortunately this information is not easily perceived by a human observer, particularly when using a standard video monitor. A secondary problem is the difficulty of achieving a sharp focus since automatic focus techniques tend to fail in such conditions. Recently several commercial colour video processing systems have become available. These systems use various techniques to improve image quality in low contrast conditions whilst retaining colour content. These systems produce improvements in subjective image quality in some situations, particularly in conditions of haze and light fog. There is also some evidence that video enhancement leads to improved ATR performance when used as a pre-processing stage. Psychological literature indicates that low contrast levels generally lead to a reduction in the performance of human observers in carrying out simple visual tasks. The aim of this paper is to present the results of an empirical study on object recognition in adverse viewing conditions. The chosen visual task was vehicle number plate recognition at long ranges (500 m and beyond). Two different commercial video enhancement systems are evaluated using the same protocol. The results show an increase in effective range with some differences between the different enhancement systems.

  12. The viewpoint complexity of an object-recognition task.

    PubMed

    Tjan, B S; Legge, G E

    1998-08-01

    There is an ongoing debate about the nature of perceptual representation in human object recognition. Resolution of this debate has been hampered by the lack of a metric for assessing the representational requirements of a recognition task. To recognize a member of a given set of 3-D objects, how much detail must the objects' representations contain in order to achieve a specific accuracy criterion? From the performance of an ideal observer, we derived a quantity called the view complexity (VX) to measure the required granularity of representation. VX is an intrinsic property of the object-recognition task, taking into account both the object ensemble and the type of decision required of an observer. It does not depend on the visual representation or processing used by the observer. VX can be interpreted as the number of randomly selected 2-D images needed to represent the decision boundaries in the image space of a 3-D object-recognition task. A low VX means the task is inherently more viewpoint invariant and a high VX means it is inherently more viewpoint dependent. By measuring the VX of recognition tasks with different object sets, we show that the current confusion about the nature of human perceptual representation is partly due to a failure in distinguishing between human visual processing and the properties of a task and its stimuli. We find general correspondence between the VX of a recognition task and the published human data on viewpoint dependence. Exceptions in this relationship motivated us to propose the view-rate hypothesis: human visual performance is limited by the equivalent number of 2-D image views that can be processed per unit time.

  13. Sensor agnostic object recognition using a map seeking circuit

    NASA Astrophysics Data System (ADS)

    Overman, Timothy L.; Hart, Michael

    2012-05-01

    Automatic object recognition capabilities are traditionally tuned to exploit the specific sensing modality they were designed to. Their successes (and shortcomings) are tied to object segmentation from the background, they typically require highly skilled personnel to train them, and they become cumbersome with the introduction of new objects. In this paper we describe a sensor independent algorithm based on the biologically inspired technology of map seeking circuits (MSC) which overcomes many of these obstacles. In particular, the MSC concept offers transparency in object recognition from a common interface to all sensor types, analogous to a USB device. It also provides a common core framework that is independent of the sensor and expandable to support high dimensionality decision spaces. Ease in training is assured by using commercially available 3D models from the video game community. The search time remains linear no matter how many objects are introduced, ensuring rapid object recognition. Here, we report results of an MSC algorithm applied to object recognition and pose estimation from high range resolution radar (1D), electrooptical imagery (2D), and LIDAR point clouds (3D) separately. By abstracting the sensor phenomenology from the underlying a prior knowledge base, MSC shows promise as an easily adaptable tool for incorporating additional sensor inputs.

  14. Hypnotizability and haptics: visual recognition of unimanually explored 'nonmeaningful' objects.

    PubMed

    Castellani, E; Carli, G; Santarcangelo, E L

    2012-08-01

    The cognitive trait of hypnotizability modulates sensorimotor integration and mental imagery. In particular, earlier results show that visual recognition of 'nonmeaningful', unfamiliar objects bimanually explored is faster and more accurate in subjects with high (Highs) than with low hypnotizability (Lows). The present study was aimed at investigating whether Highs exhibit a similar advantage after unimanual exploration. Recognition frequency (RF) and Recognition time (RT) of correct recognitions of the explored objects were recorded. The results showed the absence of any hypnotizability-related difference in recognition frequencies. In addition, RF of the right and left hand was comparable in Highs as in Lows, while slight differences were found in RT. We suggest that hemispheric co-operation played a key role in the better performance of Highs in the bimanual task previously studied. In the unimanual exploration, the task's characteristics (favoring the left hand), hypnotizability-related cerebral asymmetry (favoring the right hand in Highs) and the possible preferential verbal style of recognition in Lows (favoring the right hand in this group) antagonize each other and prevent the occurrence of major differences between the performance of Highs and Lows.

  15. Object Recognition Method of Space Debris Tracking Image Sequence

    NASA Astrophysics Data System (ADS)

    Chen, Zhang; Yi-ding, Ping

    2016-07-01

    In order to strengthen the capability of space debris detection, the automated optical observation becomes more and more popular. Thus, the fully unattended automatic object recognition is urgently needed to study. As the open-loop tracking, which guides the telescope only with the historical orbital elements, is a simple and robust way to track space debris, based on the analysis on the point distribution characteristics of object's open-loop tracking image sequence in the pixel space, this paper has proposed to use the cluster identification method for the automatic space debris recognition, and made a comparison on the three kinds of different algorithms.

  16. Visual Exploration and Object Recognition by Lattice Deformation

    PubMed Central

    Melloni, Lucia; Mureşan, Raul C.

    2011-01-01

    Mechanisms of explicit object recognition are often difficult to investigate and require stimuli with controlled features whose expression can be manipulated in a precise quantitative fashion. Here, we developed a novel method (called “Dots”), for generating visual stimuli, which is based on the progressive deformation of a regular lattice of dots, driven by local contour information from images of objects. By applying progressively larger deformation to the lattice, the latter conveys progressively more information about the target object. Stimuli generated with the presented method enable a precise control of object-related information content while preserving low-level image statistics, globally, and affecting them only little, locally. We show that such stimuli are useful for investigating object recognition under a naturalistic setting – free visual exploration – enabling a clear dissociation between object detection and explicit recognition. Using the introduced stimuli, we show that top-down modulation induced by previous exposure to target objects can greatly influence perceptual decisions, lowering perceptual thresholds not only for object recognition but also for object detection (visual hysteresis). Visual hysteresis is target-specific, its expression and magnitude depending on the identity of individual objects. Relying on the particular features of dot stimuli and on eye-tracking measurements, we further demonstrate that top-down processes guide visual exploration, controlling how visual information is integrated by successive fixations. Prior knowledge about objects can guide saccades/fixations to sample locations that are supposed to be highly informative, even when the actual information is missing from those locations in the stimulus. The duration of individual fixations is modulated by the novelty and difficulty of the stimulus, likely reflecting cognitive demand. PMID:21818397

  17. Image-based object recognition in man, monkey and machine.

    PubMed

    Tarr, M J; Bülthoff, H H

    1998-07-01

    Theories of visual object recognition must solve the problem of recognizing 3D objects given that perceivers only receive 2D patterns of light on their retinae. Recent findings from human psychophysics, neurophysiology and machine vision provide converging evidence for 'image-based' models in which objects are represented as collections of viewpoint-specific local features. This approach is contrasted with 'structural-description' models in which objects are represented as configurations of 3D volumes or parts. We then review recent behavioral results that address the biological plausibility of both approaches, a well as some of their computational advantages and limitations. We conclude that, although the image-based approach holds great promise, it has potential pitfalls that may be best overcome by including structural information. Thus, the most viable model of object recognition may be one that incorporates the most appealing aspects of both image-based and structural description theories.

  18. Three-dimensional object rotation-tolerant recognition for integral imaging using synthetic discriminant function

    NASA Astrophysics Data System (ADS)

    Hao, Jinbo; Wang, Xiaorui; Zhang, Jianqi; Xu, Yin

    2013-04-01

    This paper presents a novel approach of three-dimensional object rotation-tolerant recognition that combines the merits of Integral Imaging (II) and Synthetic Discriminant Function (SDF). SDF aims at filters and distortion-tolerant recognition, and we use it for three-dimensional (3-D) rotation-tolerant recognition with II system. Using high relevancy of elemental images of II, the approach can not only realize 3-D rotation-tolerant recognition, but also reduce computational complexity. The correctness has been validated by experimental results.

  19. Three-dimensional object recognition using similar triangles and decision trees

    NASA Technical Reports Server (NTRS)

    Spirkovska, Lilly

    1993-01-01

    A system, TRIDEC, that is capable of distinguishing between a set of objects despite changes in the objects' positions in the input field, their size, or their rotational orientation in 3D space is described. TRIDEC combines very simple yet effective features with the classification capabilities of inductive decision tree methods. The feature vector is a list of all similar triangles defined by connecting all combinations of three pixels in a coarse coded 127 x 127 pixel input field. The classification is accomplished by building a decision tree using the information provided from a limited number of translated, scaled, and rotated samples. Simulation results are presented which show that TRIDEC achieves 94 percent recognition accuracy in the 2D invariant object recognition domain and 98 percent recognition accuracy in the 3D invariant object recognition domain after training on only a small sample of transformed views of the objects.

  20. Three-dimensional object recognition using similar triangles and decision trees

    NASA Technical Reports Server (NTRS)

    Spirkovska, Lilly

    1993-01-01

    A system, TRIDEC, that is capable of distinguishing between a set of objects despite changes in the objects' positions in the input field, their size, or their rotational orientation in 3D space is described. TRIDEC combines very simple yet effective features with the classification capabilities of inductive decision tree methods. The feature vector is a list of all similar triangles defined by connecting all combinations of three pixels in a coarse coded 127 x 127 pixel input field. The classification is accomplished by building a decision tree using the information provided from a limited number of translated, scaled, and rotated samples. Simulation results are presented which show that TRIDEC achieves 94 percent recognition accuracy in the 2D invariant object recognition domain and 98 percent recognition accuracy in the 3D invariant object recognition domain after training on only a small sample of transformed views of the objects.

  1. 3-D object recognition using 2-D views.

    PubMed

    Li, Wenjing; Bebis, George; Bourbakis, Nikolaos G

    2008-11-01

    We consider the problem of recognizing 3-D objects from 2-D images using geometric models and assuming different viewing angles and positions. Our goal is to recognize and localize instances of specific objects (i.e., model-based) in a scene. This is in contrast to category-based object recognition methods where the goal is to search for instances of objects that belong to a certain visual category (e.g., faces or cars). The key contribution of our work is improving 3-D object recognition by integrating Algebraic Functions of Views (AFoVs), a powerful framework for predicting the geometric appearance of an object due to viewpoint changes, with indexing and learning. During training, we compute the space of views that groups of object features can produce under the assumption of 3-D linear transformations, by combining a small number of reference views that contain the object features using AFoVs. Unrealistic views (e.g., due to the assumption of 3-D linear transformations) are eliminated by imposing a pair of rigidity constraints based on knowledge of the transformation between the reference views of the object. To represent the space of views that an object can produce compactly while allowing efficient hypothesis generation during recognition, we propose combining indexing with learning in two stages. In the first stage, we sample the space of views of an object sparsely and represent information about the samples using indexing. In the second stage, we build probabilistic models of shape appearance by sampling the space of views of the object densely and learning the manifold formed by the samples. Learning employs the Expectation-Maximization (EM) algorithm and takes place in a "universal," lower-dimensional, space computed through Random Projection (RP). During recognition, we extract groups of point features from the scene and we use indexing to retrieve the most feasible model groups that might have produced them (i.e., hypothesis generation). The likelihood

  2. Orientation-Invariant Object Recognition: Evidence from Repetition Blindness

    ERIC Educational Resources Information Center

    Harris, Irina M.; Dux, Paul E.

    2005-01-01

    The question of whether object recognition is orientation-invariant or orientation-dependent was investigated using a repetition blindness (RB) paradigm. In RB, the second occurrence of a repeated stimulus is less likely to be reported, compared to the occurrence of a different stimulus, if it occurs within a short time of the first presentation.…

  3. Computing with Connections in Visual Recognition of Origami Objects.

    ERIC Educational Resources Information Center

    Sabbah, Daniel

    1985-01-01

    Summarizes an initial foray in tackling artificial intelligence problems using a connectionist approach. The task chosen is visual recognition of Origami objects, and the questions answered are how to construct a connectionist network to represent and recognize projected Origami line drawings and the advantages such an approach would have. (30…

  4. Computing with Connections in Visual Recognition of Origami Objects.

    ERIC Educational Resources Information Center

    Sabbah, Daniel

    1985-01-01

    Summarizes an initial foray in tackling artificial intelligence problems using a connectionist approach. The task chosen is visual recognition of Origami objects, and the questions answered are how to construct a connectionist network to represent and recognize projected Origami line drawings and the advantages such an approach would have. (30…

  5. High-speed optical object recognition processor with massive holographic memory

    NASA Astrophysics Data System (ADS)

    Chao, Tien-Hsin; Zhou, Hanying; Reyes, George F.

    2002-09-01

    Real-time object recognition using a compact grayscale optical correlator will be introduced. A holographic memory module for storing a large bank of optimum correlation filters to accommodate large data throughput rate needed for many real-world applications has also been developed. System architecture of the optical processor and the holographic memory will be presented. Application examples of this object recognition technology will also be demonstrated.

  6. Evidence That the Rat Hippocampus Has Contrasting Roles in Object Recognition Memory and Object Recency Memory

    PubMed Central

    Albasser, Mathieu M.; Amin, Eman; Lin, Tzu-Ching E.; Iordanova, Mihaela D.; Aggleton, John P.

    2012-01-01

    Adult rats with extensive, bilateral neurotoxic lesions of the hippocampus showed normal forgetting curves for object recognition memory, yet were impaired on closely related tests of object recency memory. The present findings point to specific mechanisms for temporal order information (recency) that are dependent on the hippocampus and do not involve object recognition memory. The object recognition tests measured rats exploring simultaneously presented objects, one novel and the other familiar. Task difficulty was varied by altering the retention delays after presentation of the familiar object, so creating a forgetting curve. Hippocampal lesions had no apparent effect, despite using an apparatus (bow-tie maze) where it was possible to give lists of objects that might be expected to increase stimulus interference. In contrast, the same hippocampal lesions impaired the normal preference for an older (less recent) familiar object over a more recent, familiar object. A correlation was found between the loss of septal hippocampal tissue and this impairment in recency memory. The dissociation in the present study between recognition memory (spared) and recency memory (impaired) was unusually compelling, because it was possible to test the same objects for both forms of memory within the same session and within the same apparatus. The object recency deficit is of additional interest as it provides an example of a nonspatial memory deficit following hippocampal damage. PMID:23025831

  7. Evidence that the rat hippocampus has contrasting roles in object recognition memory and object recency memory.

    PubMed

    Albasser, Mathieu M; Amin, Eman; Lin, Tzu-Ching E; Iordanova, Mihaela D; Aggleton, John P

    2012-10-01

    Adult rats with extensive, bilateral neurotoxic lesions of the hippocampus showed normal forgetting curves for object recognition memory, yet were impaired on closely related tests of object recency memory. The present findings point to specific mechanisms for temporal order information (recency) that are dependent on the hippocampus and do not involve object recognition memory. The object recognition tests measured rats exploring simultaneously presented objects, one novel and the other familiar. Task difficulty was varied by altering the retention delays after presentation of the familiar object, so creating a forgetting curve. Hippocampal lesions had no apparent effect, despite using an apparatus (bow-tie maze) where it was possible to give lists of objects that might be expected to increase stimulus interference. In contrast, the same hippocampal lesions impaired the normal preference for an older (less recent) familiar object over a more recent, familiar object. A correlation was found between the loss of septal hippocampal tissue and this impairment in recency memory. The dissociation in the present study between recognition memory (spared) and recency memory (impaired) was unusually compelling, because it was possible to test the same objects for both forms of memory within the same session and within the same apparatus. The object recency deficit is of additional interest as it provides an example of a nonspatial memory deficit following hippocampal damage. PsycINFO Database Record (c) 2012 APA, all rights reserved.

  8. Speckle-learning-based object recognition through scattering media.

    PubMed

    Ando, Takamasa; Horisaki, Ryoichi; Tanida, Jun

    2015-12-28

    We experimentally demonstrated object recognition through scattering media based on direct machine learning of a number of speckle intensity images. In the experiments, speckle intensity images of amplitude or phase objects on a spatial light modulator between scattering plates were captured by a camera. We used the support vector machine for binary classification of the captured speckle intensity images of face and non-face data. The experimental results showed that speckles are sufficient for machine learning.

  9. Nicotine Administration Attenuates Methamphetamine-Induced Novel Object Recognition Deficits

    PubMed Central

    Vieira-Brock, Paula L.; McFadden, Lisa M.; Nielsen, Shannon M.; Smith, Misty D.; Hanson, Glen R.

    2015-01-01

    Background: Previous studies have demonstrated that methamphetamine abuse leads to memory deficits and these are associated with relapse. Furthermore, extensive evidence indicates that nicotine prevents and/or improves memory deficits in different models of cognitive dysfunction and these nicotinic effects might be mediated by hippocampal or cortical nicotinic acetylcholine receptors. The present study investigated whether nicotine attenuates methamphetamine-induced novel object recognition deficits in rats and explored potential underlying mechanisms. Methods: Adolescent or adult male Sprague-Dawley rats received either nicotine water (10–75 μg/mL) or tap water for several weeks. Methamphetamine (4×7.5mg/kg/injection) or saline was administered either before or after chronic nicotine exposure. Novel object recognition was evaluated 6 days after methamphetamine or saline. Serotonin transporter function and density and α4β2 nicotinic acetylcholine receptor density were assessed on the following day. Results: Chronic nicotine intake via drinking water beginning during either adolescence or adulthood attenuated the novel object recognition deficits caused by a high-dose methamphetamine administration. Similarly, nicotine attenuated methamphetamine-induced deficits in novel object recognition when administered after methamphetamine treatment. However, nicotine did not attenuate the serotonergic deficits caused by methamphetamine in adults. Conversely, nicotine attenuated methamphetamine-induced deficits in α4β2 nicotinic acetylcholine receptor density in the hippocampal CA1 region. Furthermore, nicotine increased α4β2 nicotinic acetylcholine receptor density in the hippocampal CA3, dentate gyrus and perirhinal cortex in both saline- and methamphetamine-treated rats. Conclusions: Overall, these findings suggest that nicotine-induced increases in α4β2 nicotinic acetylcholine receptors in the hippocampus and perirhinal cortex might be one mechanism by which

  10. Nicotine Administration Attenuates Methamphetamine-Induced Novel Object Recognition Deficits.

    PubMed

    Vieira-Brock, Paula L; McFadden, Lisa M; Nielsen, Shannon M; Smith, Misty D; Hanson, Glen R; Fleckenstein, Annette E

    2015-07-11

    Previous studies have demonstrated that methamphetamine abuse leads to memory deficits and these are associated with relapse. Furthermore, extensive evidence indicates that nicotine prevents and/or improves memory deficits in different models of cognitive dysfunction and these nicotinic effects might be mediated by hippocampal or cortical nicotinic acetylcholine receptors. The present study investigated whether nicotine attenuates methamphetamine-induced novel object recognition deficits in rats and explored potential underlying mechanisms. Adolescent or adult male Sprague-Dawley rats received either nicotine water (10-75 μg/mL) or tap water for several weeks. Methamphetamine (4 × 7.5mg/kg/injection) or saline was administered either before or after chronic nicotine exposure. Novel object recognition was evaluated 6 days after methamphetamine or saline. Serotonin transporter function and density and α4β2 nicotinic acetylcholine receptor density were assessed on the following day. Chronic nicotine intake via drinking water beginning during either adolescence or adulthood attenuated the novel object recognition deficits caused by a high-dose methamphetamine administration. Similarly, nicotine attenuated methamphetamine-induced deficits in novel object recognition when administered after methamphetamine treatment. However, nicotine did not attenuate the serotonergic deficits caused by methamphetamine in adults. Conversely, nicotine attenuated methamphetamine-induced deficits in α4β2 nicotinic acetylcholine receptor density in the hippocampal CA1 region. Furthermore, nicotine increased α4β2 nicotinic acetylcholine receptor density in the hippocampal CA3, dentate gyrus and perirhinal cortex in both saline- and methamphetamine-treated rats. Overall, these findings suggest that nicotine-induced increases in α4β2 nicotinic acetylcholine receptors in the hippocampus and perirhinal cortex might be one mechanism by which novel object recognition deficits are

  11. Object Locating System

    NASA Technical Reports Server (NTRS)

    Arndt, G. Dickey (Inventor); Carl, James R. (Inventor)

    2000-01-01

    A portable system is provided that is operational for determining, with three dimensional resolution, the position of a buried object or approximately positioned object that may move in space or air or gas. The system has a plurality of receivers for detecting the signal front a target antenna and measuring the phase thereof with respect to a reference signal. The relative permittivity and conductivity of the medium in which the object is located is used along with the measured phase signal to determine a distance between the object and each of the plurality of receivers. Knowing these distances. an iteration technique is provided for solving equations simultaneously to provide position coordinates. The system may also be used for tracking movement of an object within close range of the system by sampling and recording subsequent position of the object. A dipole target antenna. when positioned adjacent to a buried object, may be energized using a separate transmitter which couples energy to the target antenna through the medium. The target antenna then preferably resonates at a different frequency, such as a second harmonic of the transmitter frequency.

  12. Priming for novel object associations: Neural differences from object item priming and equivalent forms of recognition.

    PubMed

    Gomes, Carlos Alexandre; Figueiredo, Patrícia; Mayes, Andrew

    2016-04-01

    The neural substrates of associative and item priming and recognition were investigated in a functional magnetic resonance imaging study over two separate sessions. In the priming session, participants decided which object of a pair was bigger during both study and test phases. In the recognition session, participants saw different object pairs and performed the same size-judgement task followed by an associative recognition memory task. Associative priming was accompanied by reduced activity in the right middle occipital gyrus as well as in bilateral hippocampus. Object item priming was accompanied by reduced activity in extensive priming-related areas in the bilateral occipitotemporofrontal cortex, as well as in the perirhinal cortex, but not in the hippocampus. Associative recognition was characterized by activity increases in regions linked to recollection, such as the hippocampus, posterior cingulate cortex, anterior medial frontal gyrus and posterior parahippocampal cortex. Item object priming and recognition recruited broadly overlapping regions (e.g., bilateral middle occipital and prefrontal cortices, left fusiform gyrus), even though the BOLD response was in opposite directions. These regions along with the precuneus, where both item priming and recognition were accompanied by activation, have been found to respond to object familiarity. The minimal structural overlap between object associative priming and recollection-based associative recognition suggests that they depend on largely different stimulus-related information and that the different directions of the effects indicate distinct retrieval mechanisms. In contrast, item priming and familiarity-based recognition seemed mainly based on common memory information, although the extent of common processing between priming and familiarity remains unclear. Further implications of these findings are discussed.

  13. Invariant visual object recognition and shape processing in rats

    PubMed Central

    Zoccolan, Davide

    2015-01-01

    Invariant visual object recognition is the ability to recognize visual objects despite the vastly different images that each object can project onto the retina during natural vision, depending on its position and size within the visual field, its orientation relative to the viewer, etc. Achieving invariant recognition represents such a formidable computational challenge that is often assumed to be a unique hallmark of primate vision. Historically, this has limited the invasive investigation of its neuronal underpinnings to monkey studies, in spite of the narrow range of experimental approaches that these animal models allow. Meanwhile, rodents have been largely neglected as models of object vision, because of the widespread belief that they are incapable of advanced visual processing. However, the powerful array of experimental tools that have been developed to dissect neuronal circuits in rodents has made these species very attractive to vision scientists too, promoting a new tide of studies that have started to systematically explore visual functions in rats and mice. Rats, in particular, have been the subjects of several behavioral studies, aimed at assessing how advanced object recognition and shape processing is in this species. Here, I review these recent investigations, as well as earlier studies of rat pattern vision, to provide an historical overview and a critical summary of the status of the knowledge about rat object vision. The picture emerging from this survey is very encouraging with regard to the possibility of using rats as complementary models to monkeys in the study of higher-level vision. PMID:25561421

  14. Multispectral image analysis for object recognition and classification

    NASA Astrophysics Data System (ADS)

    Viau, C. R.; Payeur, P.; Cretu, A.-M.

    2016-05-01

    Computer and machine vision applications are used in numerous fields to analyze static and dynamic imagery in order to assist or automate decision-making processes. Advancements in sensor technologies now make it possible to capture and visualize imagery at various wavelengths (or bands) of the electromagnetic spectrum. Multispectral imaging has countless applications in various fields including (but not limited to) security, defense, space, medical, manufacturing and archeology. The development of advanced algorithms to process and extract salient information from the imagery is a critical component of the overall system performance. The fundamental objective of this research project was to investigate the benefits of combining imagery from the visual and thermal bands of the electromagnetic spectrum to improve the recognition rates and accuracy of commonly found objects in an office setting. A multispectral dataset (visual and thermal) was captured and features from the visual and thermal images were extracted and used to train support vector machine (SVM) classifiers. The SVM's class prediction ability was evaluated separately on the visual, thermal and multispectral testing datasets.

  15. Biological object recognition in μ-radiography images

    NASA Astrophysics Data System (ADS)

    Prochazka, A.; Dammer, J.; Weyda, F.; Sopko, V.; Benes, J.; Zeman, J.; Jandejsek, I.

    2015-03-01

    This study presents an applicability of real-time microradiography to biological objects, namely to horse chestnut leafminer, Cameraria ohridella (Insecta: Lepidoptera, Gracillariidae) and following image processing focusing on image segmentation and object recognition. The microradiography of insects (such as horse chestnut leafminer) provides a non-invasive imaging that leaves the organisms alive. The imaging requires a high spatial resolution (micrometer scale) radiographic system. Our radiographic system consists of a micro-focus X-ray tube and two types of detectors. The first is a charge integrating detector (Hamamatsu flat panel), the second is a pixel semiconductor detector (Medipix2 detector). The latter allows detection of single quantum photon of ionizing radiation. We obtained numerous horse chestnuts leafminer pupae in several microradiography images easy recognizable in automatic mode using the image processing methods. We implemented an algorithm that is able to count a number of dead and alive pupae in images. The algorithm was based on two methods: 1) noise reduction using mathematical morphology filters, 2) Canny edge detection. The accuracy of the algorithm is higher for the Medipix2 (average recall for detection of alive pupae =0.99, average recall for detection of dead pupae =0.83), than for the flat panel (average recall for detection of alive pupae =0.99, average recall for detection of dead pupae =0.77). Therefore, we conclude that Medipix2 has lower noise and better displays contours (edges) of biological objects. Our method allows automatic selection and calculation of dead and alive chestnut leafminer pupae. It leads to faster monitoring of the population of one of the world's important insect pest.

  16. A chicken model for studying the emergence of invariant object recognition.

    PubMed

    Wood, Samantha M W; Wood, Justin N

    2015-01-01

    "Invariant object recognition" refers to the ability to recognize objects across variation in their appearance on the retina. This ability is central to visual perception, yet its developmental origins are poorly understood. Traditionally, nonhuman primates, rats, and pigeons have been the most commonly used animal models for studying invariant object recognition. Although these animals have many advantages as model systems, they are not well suited for studying the emergence of invariant object recognition in the newborn brain. Here, we argue that newly hatched chicks (Gallus gallus) are an ideal model system for studying the emergence of invariant object recognition. Using an automated controlled-rearing approach, we show that chicks can build a viewpoint-invariant representation of the first object they see in their life. This invariant representation can be built from highly impoverished visual input (three images of an object separated by 15° azimuth rotations) and cannot be accounted for by low-level retina-like or V1-like neuronal representations. These results indicate that newborn neural circuits begin building invariant object representations at the onset of vision and argue for an increased focus on chicks as an animal model for studying invariant object recognition.

  17. Semantic interference from visual object recognition on visual imagery.

    PubMed

    Lloyd-Jones, Toby J; Vernon, David

    2003-07-01

    A new technique for examining the interaction between visual object recognition and visual imagery is reported. The "image-picture interference" paradigm requires participants to generate and make a response to a mental image of a previously memorized object, while ignoring a simultaneously presented picture distractor. Responses in 2 imagery tasks (making left-right higher spatial judgments and making taller-wider judgments) were longer when the simultaneous picture distractor was categorically related to the target distractor relative to unrelated and neutral target-distractor combinations. In contrast, performance was not influenced in this way when the distractor was a related word, when a semantic categorization decision was made to the target, or when distractor and target were visually but not categorically related to one another. The authors discuss these findings in terms of the semantic representations shared by visual object recognition and visual imagery that mediate performance.

  18. Comparison of Object Recognition Behavior in Human and Monkey.

    PubMed

    Rajalingham, Rishi; Schmidt, Kailyn; DiCarlo, James J

    2015-09-02

    Although the rhesus monkey is used widely as an animal model of human visual processing, it is not known whether invariant visual object recognition behavior is quantitatively comparable across monkeys and humans. To address this question, we systematically compared the core object recognition behavior of two monkeys with that of human subjects. To test true object recognition behavior (rather than image matching), we generated several thousand naturalistic synthetic images of 24 basic-level objects with high variation in viewing parameters and image background. Monkeys were trained to perform binary object recognition tasks on a match-to-sample paradigm. Data from 605 human subjects performing the same tasks on Mechanical Turk were aggregated to characterize "pooled human" object recognition behavior, as well as 33 separate Mechanical Turk subjects to characterize individual human subject behavior. Our results show that monkeys learn each new object in a few days, after which they not only match mean human performance but show a pattern of object confusion that is highly correlated with pooled human confusion patterns and is statistically indistinguishable from individual human subjects. Importantly, this shared human and monkey pattern of 3D object confusion is not shared with low-level visual representations (pixels, V1+; models of the retina and primary visual cortex) but is shared with a state-of-the-art computer vision feature representation. Together, these results are consistent with the hypothesis that rhesus monkeys and humans share a common neural shape representation that directly supports object perception. To date, several mammalian species have shown promise as animal models for studying the neural mechanisms underlying high-level visual processing in humans. In light of this diversity, making tight comparisons between nonhuman and human primates is particularly critical in determining the best use of nonhuman primates to further the goal of the

  19. Comparison of Object Recognition Behavior in Human and Monkey

    PubMed Central

    Rajalingham, Rishi; Schmidt, Kailyn

    2015-01-01

    Although the rhesus monkey is used widely as an animal model of human visual processing, it is not known whether invariant visual object recognition behavior is quantitatively comparable across monkeys and humans. To address this question, we systematically compared the core object recognition behavior of two monkeys with that of human subjects. To test true object recognition behavior (rather than image matching), we generated several thousand naturalistic synthetic images of 24 basic-level objects with high variation in viewing parameters and image background. Monkeys were trained to perform binary object recognition tasks on a match-to-sample paradigm. Data from 605 human subjects performing the same tasks on Mechanical Turk were aggregated to characterize “pooled human” object recognition behavior, as well as 33 separate Mechanical Turk subjects to characterize individual human subject behavior. Our results show that monkeys learn each new object in a few days, after which they not only match mean human performance but show a pattern of object confusion that is highly correlated with pooled human confusion patterns and is statistically indistinguishable from individual human subjects. Importantly, this shared human and monkey pattern of 3D object confusion is not shared with low-level visual representations (pixels, V1+; models of the retina and primary visual cortex) but is shared with a state-of-the-art computer vision feature representation. Together, these results are consistent with the hypothesis that rhesus monkeys and humans share a common neural shape representation that directly supports object perception. SIGNIFICANCE STATEMENT To date, several mammalian species have shown promise as animal models for studying the neural mechanisms underlying high-level visual processing in humans. In light of this diversity, making tight comparisons between nonhuman and human primates is particularly critical in determining the best use of nonhuman primates to

  20. Multispectral and hyperspectral imaging with AOTF for object recognition

    NASA Astrophysics Data System (ADS)

    Gupta, Neelam; Dahmani, Rachid

    1999-01-01

    Acousto-optic tunable-filter (AOTF) technology has been used in the design of a no-moving parts, compact, lightweight, field portable, automated, adaptive spectral imaging system when combined with a high sensitivity imaging detector array. Such a system could detect spectral signatures of targets and/or background, which contain polarization information and can be digitally processed by a variety of algorithms. At the Army Research Laboratory, we have developed and used a number of AOTF imaging systems and are also carrying out the development of such imagers at longer wavelengths. We have carried out hyperspectral and multispectral imaging using AOTF systems covering the spectral range from the visible to mid-IR. One of the imager uses a two-cascaded collinear-architecture AOTF cell in the visible-to-near-IR range with a digital Si charge-coupled device camera as the detector. The images obtained with this system showed no color blurring or image shift due to the angular deviation of different colors as a result of diffraction, and the digital images are stored and processed with great ease. The spatial resolution of the filter was evaluated by means of the lines of a target chart. We have also obtained and processed images from another noncollinear visible-to-near-IR AOTF imager with a digital camera, and used hyperspectral image processing software to enhance object recognition in cluttered background. We are presently working on a mid-IR AOTF imaging system that uses a high- performance InSb focal plane array and image acquisition and processing software. We describe our hyperspectral imaging program and present results from our imaging experiments.

  1. Superior voice recognition in a patient with acquired prosopagnosia and object agnosia.

    PubMed

    Hoover, Adria E N; Démonet, Jean-François; Steeves, Jennifer K E

    2010-11-01

    Anecdotally, it has been reported that individuals with acquired prosopagnosia compensate for their inability to recognize faces by using other person identity cues such as hair, gait or the voice. Are they therefore superior at the use of non-face cues, specifically voices, to person identity? Here, we empirically measure person and object identity recognition in a patient with acquired prosopagnosia and object agnosia. We quantify person identity (face and voice) and object identity (car and horn) recognition for visual, auditory, and bimodal (visual and auditory) stimuli. The patient is unable to recognize faces or cars, consistent with his prosopagnosia and object agnosia, respectively. He is perfectly able to recognize people's voices and car horns and bimodal stimuli. These data show a reverse shift in the typical weighting of visual over auditory information for audiovisual stimuli in a compromised visual recognition system. Moreover, the patient shows selectively superior voice recognition compared to the controls revealing that two different stimulus domains, persons and objects, may not be equally affected by sensory adaptation effects. This also implies that person and object identity recognition are processed in separate pathways. These data demonstrate that an individual with acquired prosopagnosia and object agnosia can compensate for the visual impairment and become quite skilled at using spared aspects of sensory processing. In the case of acquired prosopagnosia it is advantageous to develop a superior use of voices for person identity recognition in everyday life.

  2. How Can Selection of Biologically Inspired Features Improve the Performance of a Robust Object Recognition Model?

    PubMed Central

    Ghodrati, Masoud; Khaligh-Razavi, Seyed-Mahdi; Ebrahimpour, Reza; Rajaei, Karim; Pooyan, Mohammad

    2012-01-01

    Humans can effectively and swiftly recognize objects in complex natural scenes. This outstanding ability has motivated many computational object recognition models. Most of these models try to emulate the behavior of this remarkable system. The human visual system hierarchically recognizes objects in several processing stages. Along these stages a set of features with increasing complexity is extracted by different parts of visual system. Elementary features like bars and edges are processed in earlier levels of visual pathway and as far as one goes upper in this pathway more complex features will be spotted. It is an important interrogation in the field of visual processing to see which features of an object are selected and represented by the visual cortex. To address this issue, we extended a hierarchical model, which is motivated by biology, for different object recognition tasks. In this model, a set of object parts, named patches, extracted in the intermediate stages. These object parts are used for training procedure in the model and have an important role in object recognition. These patches are selected indiscriminately from different positions of an image and this can lead to the extraction of non-discriminating patches which eventually may reduce the performance. In the proposed model we used an evolutionary algorithm approach to select a set of informative patches. Our reported results indicate that these patches are more informative than usual random patches. We demonstrate the strength of the proposed model on a range of object recognition tasks. The proposed model outperforms the original model in diverse object recognition tasks. It can be seen from the experiments that selected features are generally particular parts of target images. Our results suggest that selected features which are parts of target objects provide an efficient set for robust object recognition. PMID:22384229

  3. How can selection of biologically inspired features improve the performance of a robust object recognition model?

    PubMed

    Ghodrati, Masoud; Khaligh-Razavi, Seyed-Mahdi; Ebrahimpour, Reza; Rajaei, Karim; Pooyan, Mohammad

    2012-01-01

    Humans can effectively and swiftly recognize objects in complex natural scenes. This outstanding ability has motivated many computational object recognition models. Most of these models try to emulate the behavior of this remarkable system. The human visual system hierarchically recognizes objects in several processing stages. Along these stages a set of features with increasing complexity is extracted by different parts of visual system. Elementary features like bars and edges are processed in earlier levels of visual pathway and as far as one goes upper in this pathway more complex features will be spotted. It is an important interrogation in the field of visual processing to see which features of an object are selected and represented by the visual cortex. To address this issue, we extended a hierarchical model, which is motivated by biology, for different object recognition tasks. In this model, a set of object parts, named patches, extracted in the intermediate stages. These object parts are used for training procedure in the model and have an important role in object recognition. These patches are selected indiscriminately from different positions of an image and this can lead to the extraction of non-discriminating patches which eventually may reduce the performance. In the proposed model we used an evolutionary algorithm approach to select a set of informative patches. Our reported results indicate that these patches are more informative than usual random patches. We demonstrate the strength of the proposed model on a range of object recognition tasks. The proposed model outperforms the original model in diverse object recognition tasks. It can be seen from the experiments that selected features are generally particular parts of target images. Our results suggest that selected features which are parts of target objects provide an efficient set for robust object recognition.

  4. Distortion-invariant kernel correlation filters for general object recognition

    NASA Astrophysics Data System (ADS)

    Patnaik, Rohit

    General object recognition is a specific application of pattern recognition, in which an object in a background must be classified in the presence of several distortions such as aspect-view differences, scale differences, and depression-angle differences. Since the object can be present at different locations in the test input, a classification algorithm must be applied to all possible object locations in the test input. We emphasize one type of classifier, the distortion-invariant filter (DIF), for fast object recognition, since it can be applied to all possible object locations using a fast Fourier transform (FFT) correlation. We refer to distortion-invariant correlation filters simply as DIFs. DIFs all use a combination of training-set images that are representative of the expected distortions in the test set. In this dissertation, we consider a new approach that combines DIFs and the higher-order kernel technique; these form what we refer to as "kernel DIFs." Our objective is to develop higher-order classifiers that can be applied (efficiently and fast) to all possible locations of the object in the test input. All prior kernel DIFs ignored the issue of efficient filter shifts. We detail which kernel DIF formulations are computational realistic to use and why. We discuss the proper way to synthesize DIFs and kernel DIFs for the wide area search case (i.e., when a small filter must be applied to a much larger test input) and the preferable way to perform wide area search with these filters; this is new. We use computer-aided design (CAD) simulated infrared (IR) object imagery and real IR clutter imagery to obtain test results. Our test results on IR data show that a particular kernel DIF, the kernel SDF filter and its new "preprocessed" version, is promising, in terms of both test-set performance and on-line calculations, and is emphasized in this dissertation. We examine the recognition of object variants. We also quantify the effect of different constant

  5. Top-down facilitation of visual object recognition: object-based and context-based contributions.

    PubMed

    Fenske, Mark J; Aminoff, Elissa; Gronau, Nurit; Bar, Moshe

    2006-01-01

    The neural mechanisms subserving visual recognition are traditionally described in terms of bottom-up analysis, whereby increasingly complex aspects of the visual input are processed along a hierarchical progression of cortical regions. However, the importance of top-down facilitation in successful recognition has been emphasized in recent models and research findings. Here we consider evidence for top-down facilitation of recognition that is triggered by early information about an object, as well as by contextual associations between an object and other objects with which it typically appears. The object-based mechanism is proposed to trigger top-down facilitation of visual recognition rapidly, using a partially analyzed version of the input image (i.e., a blurred image) that is projected from early visual areas directly to the prefrontal cortex (PFC). This coarse representation activates in the PFC information that is back-projected as "initial guesses" to the temporal cortex where it presensitizes the most likely interpretations of the input object. In addition to this object-based facilitation, a context-based mechanism is proposed to trigger top-down facilitation through contextual associations between objects in scenes. These contextual associations activate predictive information about which objects are likely to appear together, and can influence the "initial guesses" about an object's identity. We have shown that contextual associations are analyzed by a network that includes the parahippocampal cortex and the retrosplenial complex. The integrated proposal described here is that object- and context-based top-down influences operate together, promoting efficient recognition by framing early information about an object within the constraints provided by a lifetime of experience with contextual associations.

  6. Biologically Motivated Novel Localization Paradigm by High-Level Multiple Object Recognition in Panoramic Images

    PubMed Central

    Kim, Sungho; Shim, Min-Sheob

    2015-01-01

    This paper presents the novel paradigm of a global localization method motivated by human visual systems (HVSs). HVSs actively use the information of the object recognition results for self-position localization and for viewing direction. The proposed localization paradigm consisted of three parts: panoramic image acquisition, multiple object recognition, and grid-based localization. Multiple object recognition information from panoramic images is utilized in the localization part. High-level object information was useful not only for global localization, but also for robot-object interactions. The metric global localization (position, viewing direction) was conducted based on the bearing information of recognized objects from just one panoramic image. The feasibility of the novel localization paradigm was validated experimentally. PMID:26457323

  7. Trajectory Recognition as the Basis for Object Individuation: A Functional Model of Object File Instantiation and Object-Token Encoding

    PubMed Central

    Fields, Chris

    2011-01-01

    The perception of persisting visual objects is mediated by transient intermediate representations, object files, that are instantiated in response to some, but not all, visual trajectories. The standard object file concept does not, however, provide a mechanism sufficient to account for all experimental data on visual object persistence, object tracking, and the ability to perceive spatially disconnected stimuli as continuously existing objects. Based on relevant anatomical, functional, and developmental data, a functional model is constructed that bases visual object individuation on the recognition of temporal sequences of apparent center-of-mass positions that are specifically identified as trajectories by dedicated “trajectory recognition networks” downstream of the medial–temporal motion-detection area. This model is shown to account for a wide range of data, and to generate a variety of testable predictions. Individual differences in the recognition, abstraction, and encoding of trajectory information are expected to generate distinct object persistence judgments and object recognition abilities. Dominance of trajectory information over feature information in stored object tokens during early infancy, in particular, is expected to disrupt the ability to re-identify human and other individuals across perceptual episodes, and lead to developmental outcomes with characteristics of autism spectrum disorders. PMID:21716599

  8. The Neural Basis of Nonvisual Object Recognition Memory in the Rat

    PubMed Central

    Albasser, Mathieu M.; Olarte-Sánchez, Cristian M.; Amin, Eman; Horne, Murray R.; Newton, Michael J.; Warburton, E. Clea; Aggleton, John P.

    2012-01-01

    Research into the neural basis of recognition memory has traditionally focused on the remembrance of visual stimuli. The present study examined the neural basis of object recognition memory in the dark, with a view to determining the extent to which it shares common pathways with visual-based object recognition. Experiment 1 assessed the expression of the immediate-early gene c-fos in rats that discriminated novel from familiar objects in the dark (Group Novel). Comparisons made with a control group that explored only familiar objects (Group Familiar) showed that Group Novel had higher c-fos activity in the rostral perirhinal cortex and the lateral entorhinal cortex. Outside the temporal region, Group Novel showed relatively increased c-fos activity in the anterior medial thalamic nucleus and the anterior cingulate cortex. Both the hippocampal CA fields and the granular retrosplenial cortex showed borderline increases in c-fos activity with object novelty. The hippocampal findings prompted Experiment 2. Here, rats with hippocampal lesions were tested in the dark for object recognition memory at different retention delays. Across two replications, no evidence was found that hippocampal lesions impair nonvisual object recognition. The results indicate that in the dark, as in the light, interrelated parahippocampal sites are activated when rats explore novel stimuli. These findings reveal a network of linked c-fos activations that share superficial features with those associated with visual recognition but differ in the fine details; for example, in the locus of the perirhinal cortex activation. While there may also be a relative increase in c-fos activation in the extended-hippocampal system to object recognition in the dark, there was no evidence that this recognition memory problem required an intact hippocampus. PMID:23244291

  9. The neural basis of nonvisual object recognition memory in the rat.

    PubMed

    Albasser, Mathieu M; Olarte-Sánchez, Cristian M; Amin, Eman; Horne, Murray R; Newton, Michael J; Warburton, E Clea; Aggleton, John P

    2013-02-01

    Research into the neural basis of recognition memory has traditionally focused on the remembrance of visual stimuli. The present study examined the neural basis of object recognition memory in the dark, with a view to determining the extent to which it shares common pathways with visual-based object recognition. Experiment 1 assessed the expression of the immediate-early gene c-fos in rats that discriminated novel from familiar objects in the dark (Group Novel). Comparisons made with a control group that explored only familiar objects (Group Familiar) showed that Group Novel had higher c-fos activity in the rostral perirhinal cortex and the lateral entorhinal cortex. Outside the temporal region, Group Novel showed relatively increased c-fos activity in the anterior medial thalamic nucleus and the anterior cingulate cortex. Both the hippocampal CA fields and the granular retrosplenial cortex showed borderline increases in c-fos activity with object novelty. The hippocampal findings prompted Experiment 2. Here, rats with hippocampal lesions were tested in the dark for object recognition memory at different retention delays. Across two replications, no evidence was found that hippocampal lesions impair nonvisual object recognition. The results indicate that in the dark, as in the light, interrelated parahippocampal sites are activated when rats explore novel stimuli. These findings reveal a network of linked c-fos activations that share superficial features with those associated with visual recognition but differ in the fine details; for example, in the locus of the perirhinal cortex activation. While there may also be a relative increase in c-fos activation in the extended-hippocampal system to object recognition in the dark, there was no evidence that this recognition memory problem required an intact hippocampus.

  10. The relationship between protein synthesis and protein degradation in object recognition memory.

    PubMed

    Furini, Cristiane R G; Myskiw, Jociane de C; Schmidt, Bianca E; Zinn, Carolina G; Peixoto, Patricia B; Pereira, Luiza D; Izquierdo, Ivan

    2015-11-01

    For decades there has been a consensus that de novo protein synthesis is necessary for long-term memory. A second round of protein synthesis has been described for both extinction and reconsolidation following an unreinforced test session. Recently, it was shown that consolidation and reconsolidation depend not only on protein synthesis but also on protein degradation by the ubiquitin-proteasome system (UPS), a major mechanism responsible for protein turnover. However, the involvement of UPS on consolidation and reconsolidation of object recognition memory remains unknown. Here we investigate in the CA1 region of the dorsal hippocampus the involvement of UPS-mediated protein degradation in consolidation and reconsolidation of object recognition memory. Animals with infusion cannulae stereotaxically implanted in the CA1 region of the dorsal hippocampus, were exposed to an object recognition task. The UPS inhibitor β-Lactacystin did not affect the consolidation and the reconsolidation of object recognition memory at doses known to affect other forms of memory (inhibitory avoidance, spatial learning in a water maze) while the protein synthesis inhibitor anisomycin impaired the consolidation and the reconsolidation of the object recognition memory. However, β-Lactacystin was able to reverse the impairment caused by anisomycin on the reconsolidation process in the CA1 region of the hippocampus. Therefore, it is possible to postulate a direct link between protein degradation and protein synthesis during the reconsolidation of the object recognition memory. Copyright © 2015 Elsevier B.V. All rights reserved.

  11. Atypical Time Course of Object Recognition in Autism Spectrum Disorder

    PubMed Central

    Caplette, Laurent; Wicker, Bruno; Gosselin, Frédéric

    2016-01-01

    In neurotypical observers, it is widely believed that the visual system samples the world in a coarse-to-fine fashion. Past studies on Autism Spectrum Disorder (ASD) have identified atypical responses to fine visual information but did not investigate the time course of the sampling of information at different levels of granularity (i.e. Spatial Frequencies, SF). Here, we examined this question during an object recognition task in ASD and neurotypical observers using a novel experimental paradigm. Our results confirm and characterize with unprecedented precision a coarse-to-fine sampling of SF information in neurotypical observers. In ASD observers, we discovered a different pattern of SF sampling across time: in the first 80 ms, high SFs lead ASD observers to a higher accuracy than neurotypical observers, and these SFs are sampled differently across time in the two subject groups. Our results might be related to the absence of a mandatory precedence of global information, and to top-down processing abnormalities in ASD. PMID:27752088

  12. An Approach to Object Recognition: Aligning Pictorial Descriptions.

    DTIC Science & Technology

    1986-12-01

    PERFORMING 0RGANIZATION NAMIE ANDORS IS551. PROGRAM ELEMENT. PROJECT. TASK Artificial Inteligence Laboratory AREKA A WORK UNIT NUMBERS ( 545 Technology... ARTIFICIAL INTELLIGENCE LABORATORY A.I. Memo No. 931 December, 1986 AN APPROACH TO OBJECT RECOGNITION: ALIGNING PICTORIAL DESCRIPTIONS Shimon Ullman...within the Artificial Intelligence Laboratory at the Massachusetts Institute of Technology. Support for the A.I. Laboratory’s artificial intelligence

  13. Multisensory interactions between auditory and haptic object recognition.

    PubMed

    Kassuba, Tanja; Menz, Mareike M; Röder, Brigitte; Siebner, Hartwig R

    2013-05-01

    Object manipulation produces characteristic sounds and causes specific haptic sensations that facilitate the recognition of the manipulated object. To identify the neural correlates of audio-haptic binding of object features, healthy volunteers underwent functional magnetic resonance imaging while they matched a target object to a sample object within and across audition and touch. By introducing a delay between the presentation of sample and target stimuli, it was possible to dissociate haptic-to-auditory and auditory-to-haptic matching. We hypothesized that only semantically coherent auditory and haptic object features activate cortical regions that host unified conceptual object representations. The left fusiform gyrus (FG) and posterior superior temporal sulcus (pSTS) showed increased activation during crossmodal matching of semantically congruent but not incongruent object stimuli. In the FG, this effect was found for haptic-to-auditory and auditory-to-haptic matching, whereas the pSTS only displayed a crossmodal matching effect for congruent auditory targets. Auditory and somatosensory association cortices showed increased activity during crossmodal object matching which was, however, independent of semantic congruency. Together, the results show multisensory interactions at different hierarchical stages of auditory and haptic object processing. Object-specific crossmodal interactions culminate in the left FG, which may provide a higher order convergence zone for conceptual object knowledge.

  14. Neuronal substrates characterizing two stages in visual object recognition.

    PubMed

    Taminato, Tomoya; Miura, Naoki; Sugiura, Motoaki; Kawashima, Ryuta

    2014-12-01

    Visual object recognition is classically believed to involve two stages: a perception stage in which perceptual information is integrated, and a memory stage in which perceptual information is matched with an object's representation. The transition from the perception to the memory stage can be slowed to allow for neuroanatomical segregation using a degraded visual stimuli (DVS) task in which images are first presented at low spatial resolution and then gradually sharpened. In this functional magnetic resonance imaging study, we characterized these two stages using a DVS task based on the classic model. To separate periods that are assumed to dominate the perception, memory, and post-recognition stages, subjects responded once when they could guess the identity of the object in the image and a second time when they were certain of the identity. Activation of the right medial occipitotemporal region and the posterior part of the rostral medial frontal cortex was found to be characteristic of the perception and memory stages, respectively. Although the known role of the former region in perceptual integration was consistent with the classic model, a likely role of the latter region in monitoring for confirmation of recognition suggests the advantage of recently proposed interactive models.

  15. Invariant visual object recognition and shape processing in rats.

    PubMed

    Zoccolan, Davide

    2015-05-15

    Invariant visual object recognition is the ability to recognize visual objects despite the vastly different images that each object can project onto the retina during natural vision, depending on its position and size within the visual field, its orientation relative to the viewer, etc. Achieving invariant recognition represents such a formidable computational challenge that is often assumed to be a unique hallmark of primate vision. Historically, this has limited the invasive investigation of its neuronal underpinnings to monkey studies, in spite of the narrow range of experimental approaches that these animal models allow. Meanwhile, rodents have been largely neglected as models of object vision, because of the widespread belief that they are incapable of advanced visual processing. However, the powerful array of experimental tools that have been developed to dissect neuronal circuits in rodents has made these species very attractive to vision scientists too, promoting a new tide of studies that have started to systematically explore visual functions in rats and mice. Rats, in particular, have been the subjects of several behavioral studies, aimed at assessing how advanced object recognition and shape processing is in this species. Here, I review these recent investigations, as well as earlier studies of rat pattern vision, to provide an historical overview and a critical summary of the status of the knowledge about rat object vision. The picture emerging from this survey is very encouraging with regard to the possibility of using rats as complementary models to monkeys in the study of higher-level vision. Copyright © 2015 The Author. Published by Elsevier B.V. All rights reserved.

  16. Object Recognition and Object Segregation in Infancy: Historical Perspective, Theoretical Significance, "Kinds" of Knowledge, and Relation to Object Categorization.

    ERIC Educational Resources Information Center

    Quinn, Paul C.; Bhatt, Ramesh S.

    2001-01-01

    Reflects on Needham's findings on infants' object recognition and segregation. Examines the role for perceptual bias in explaining infant performance, places Needham's studies in historical perspective, and assesses their theoretical significance. Discusses the merits of positing different kinds of information sources for object segregation, and…

  17. How does the brain solve visual object recognition?

    PubMed Central

    Zoccolan, Davide; Rust, Nicole C.

    2012-01-01

    Mounting evidence suggests that “core object recognition,” the ability to rapidly recognize objects despite substantial appearance variation, is solved in the brain via a cascade of reflexive, largely feedforward computations that culminate in a powerful neuronal representation in the inferior temporal cortex. However, the algorithm that produces this solution remains little-understood. Here we review evidence ranging from individual neurons, to neuronal populations, to behavior, to computational models. We propose that understanding this algorithm will require using neuronal and psychophysical data to sift through many computational models, each based on building blocks of small, canonical sub-networks with a common functional goal. PMID:22325196

  18. How does the brain solve visual object recognition?

    PubMed

    DiCarlo, James J; Zoccolan, Davide; Rust, Nicole C

    2012-02-09

    Mounting evidence suggests that 'core object recognition,' the ability to rapidly recognize objects despite substantial appearance variation, is solved in the brain via a cascade of reflexive, largely feedforward computations that culminate in a powerful neuronal representation in the inferior temporal cortex. However, the algorithm that produces this solution remains poorly understood. Here we review evidence ranging from individual neurons and neuronal populations to behavior and computational models. We propose that understanding this algorithm will require using neuronal and psychophysical data to sift through many computational models, each based on building blocks of small, canonical subnetworks with a common functional goal. Copyright © 2012 Elsevier Inc. All rights reserved.

  19. An audiovisual emotion recognition system

    NASA Astrophysics Data System (ADS)

    Han, Yi; Wang, Guoyin; Yang, Yong; He, Kun

    2007-12-01

    Human emotions could be expressed by many bio-symbols. Speech and facial expression are two of them. They are both regarded as emotional information which is playing an important role in human-computer interaction. Based on our previous studies on emotion recognition, an audiovisual emotion recognition system is developed and represented in this paper. The system is designed for real-time practice, and is guaranteed by some integrated modules. These modules include speech enhancement for eliminating noises, rapid face detection for locating face from background image, example based shape learning for facial feature alignment, and optical flow based tracking algorithm for facial feature tracking. It is known that irrelevant features and high dimensionality of the data can hurt the performance of classifier. Rough set-based feature selection is a good method for dimension reduction. So 13 speech features out of 37 ones and 10 facial features out of 33 ones are selected to represent emotional information, and 52 audiovisual features are selected due to the synchronization when speech and video fused together. The experiment results have demonstrated that this system performs well in real-time practice and has high recognition rate. Our results also show that the work in multimodules fused recognition will become the trend of emotion recognition in the future.

  20. A chicken model for studying the emergence of invariant object recognition

    PubMed Central

    Wood, Samantha M. W.; Wood, Justin N.

    2015-01-01

    “Invariant object recognition” refers to the ability to recognize objects across variation in their appearance on the retina. This ability is central to visual perception, yet its developmental origins are poorly understood. Traditionally, nonhuman primates, rats, and pigeons have been the most commonly used animal models for studying invariant object recognition. Although these animals have many advantages as model systems, they are not well suited for studying the emergence of invariant object recognition in the newborn brain. Here, we argue that newly hatched chicks (Gallus gallus) are an ideal model system for studying the emergence of invariant object recognition. Using an automated controlled-rearing approach, we show that chicks can build a viewpoint-invariant representation of the first object they see in their life. This invariant representation can be built from highly impoverished visual input (three images of an object separated by 15° azimuth rotations) and cannot be accounted for by low-level retina-like or V1-like neuronal representations. These results indicate that newborn neural circuits begin building invariant object representations at the onset of vision and argue for an increased focus on chicks as an animal model for studying invariant object recognition. PMID:25767436

  1. Methylphenidate restores novel object recognition in DARPP-32 knockout mice.

    PubMed

    Heyser, Charles J; McNaughton, Caitlyn H; Vishnevetsky, Donna; Fienberg, Allen A

    2013-09-15

    Previously, we have shown that Dopamine- and cAMP-regulated phosphoprotein of 32kDa (DARPP-32) knockout mice required significantly more trials to reach criterion than wild-type mice in an operant reversal-learning task. The present study was conducted to examine adult male and female DARPP-32 knockout mice and wild-type controls in a novel object recognition test. Wild-type and knockout mice exhibited comparable behavior during the initial exploration trials. As expected, wild-type mice exhibited preferential exploration of the novel object during the substitution test, demonstrating recognition memory. In contrast, knockout mice did not show preferential exploration of the novel object, instead exhibiting an increase in exploration of all objects during the test trial. Given that the removal of DARPP-32 is an intracellular manipulation, it seemed possible to pharmacologically restore some cellular activity and behavior by stimulating dopamine receptors. Therefore, a second experiment was conducted examining the effect of methylphenidate. The results show that methylphenidate increased horizontal activity in both wild-type and knockout mice, though this increase was blunted in knockout mice. Pretreatment with methylphenidate significantly impaired novel object recognition in wild-type mice. In contrast, pretreatment with methylphenidate restored the behavior of DARPP-32 knockout mice to that observed in wild-type mice given saline. These results provide additional evidence for a functional role of DARPP-32 in the mediation of processes underlying learning and memory. These results also indicate that the behavioral deficits in DARPP-32 knockout mice may be restored by the administration of methylphenidate.

  2. Visual appearance interacts with conceptual knowledge in object recognition

    PubMed Central

    Cheung, Olivia S.; Gauthier, Isabel

    2014-01-01

    Objects contain rich visual and conceptual information, but do these two types of information interact? Here, we examine whether visual and conceptual information interact when observers see novel objects for the first time. We then address how this interaction influences the acquisition of perceptual expertise. We used two types of novel objects (Greebles), designed to resemble either animals or tools, and two lists of words, which described non-visual attributes of people or man-made objects. Participants first judged if a word was more suitable for describing people or objects while ignoring a task-irrelevant image, and showed faster responses if the words and the unfamiliar objects were congruent in terms of animacy (e.g., animal-like objects with words that described human). Participants then learned to associate objects and words that were either congruent or not in animacy, before receiving expertise training to rapidly individuate the objects. Congruent pairing of visual and conceptual information facilitated observers' ability to become a perceptual expert, as revealed in a matching task that required visual identification at the basic or subordinate levels. Taken together, these findings show that visual and conceptual information interact at multiple levels in object recognition. PMID:25120509

  3. Touching and Hearing Unseen Objects: Multisensory Effects on Scene Recognition

    PubMed Central

    van Lier, Rob

    2016-01-01

    In three experiments, we investigated the influence of object-specific sounds on haptic scene recognition without vision. Blindfolded participants had to recognize, through touch, spatial scenes comprising six objects that were placed on a round platform. Critically, in half of the trials, object-specific sounds were played when objects were touched (bimodal condition), while sounds were turned off in the other half of the trials (unimodal condition). After first exploring the scene, two objects were swapped and the task was to report, which of the objects swapped positions. In Experiment 1, geometrical objects and simple sounds were used, while in Experiment 2, the objects comprised toy animals that were matched with semantically compatible animal sounds. In Experiment 3, we replicated Experiment 1, but now a tactile-auditory object identification task preceded the experiment in which the participants learned to identify the objects based on tactile and auditory input. For each experiment, the results revealed a significant performance increase only after the switch from bimodal to unimodal. Thus, it appears that the release of bimodal identification, from audio-tactile to tactile-only produces a benefit that is not achieved when having the reversed order in which sound was added after having experience with haptic-only. We conclude that task-related factors other than mere bimodal identification cause the facilitation when switching from bimodal to unimodal conditions. PMID:27698985

  4. The role of the dorsal dentate gyrus in object and object-context recognition.

    PubMed

    Dees, Richard L; Kesner, Raymond P

    2013-11-01

    The aim of this study was to determine the role of the dorsal dentate gyrus (dDG) in object recognition memory using a black box and object-context recognition memory using a clear box with available cues that define a spatial context. Based on a 10 min retention interval between the study phase and the test phase, the results indicated that dDG lesioned rats are impaired when compared to controls in the object-context recognition test in the clear box. However, there were no reliable differences between the dDG lesioned rats and the control group for the object recognition test in the black box. Even though the dDG lesioned rats were more active in object exploration, the habituation gradients did not differ. These results suggest that the dentate gyrus lesioned rats are clearly impaired when there is an important contribution of context. Furthermore, based on a 24 h retention interval in the black box the dDG lesioned rats were impaired compared to controls.

  5. An optical processor for object recognition and tracking

    NASA Technical Reports Server (NTRS)

    Sloan, J.; Udomkesmalee, S.

    1987-01-01

    The design and development of a miniaturized optical processor that performs real time image correlation are described. The optical correlator utilizes the Vander Lugt matched spatial filter technique. The correlation output, a focused beam of light, is imaged onto a CMOS photodetector array. In addition to performing target recognition, the device also tracks the target. The hardware, composed of optical and electro-optical components, occupies only 590 cu cm of volume. A complete correlator system would also include an input imaging lens. This optical processing system is compact, rugged, requires only 3.5 watts of operating power, and weighs less than 3 kg. It represents a major achievement in miniaturizing optical processors. When considered as a special-purpose processing unit, it is an attractive alternative to conventional digital image recognition processing. It is conceivable that the combined technology of both optical and ditital processing could result in a very advanced robot vision system.

  6. Picture-object recognition in the tortoise Chelonoidis carbonaria.

    PubMed

    Wilkinson, Anna; Mueller-Paul, Julia; Huber, Ludwig

    2013-01-01

    To recognize that a picture is a representation of a real-life object is a cognitively demanding task. It requires an organism to mentally represent the concrete object (the picture) and abstract its relation to the item that it represents. This form of representational insight has been shown in a small number of mammal and bird species. However, it has not previously been studied in reptiles. This study examined picture-object recognition in the red-footed tortoise (Chelonoidis carbonaria). In Experiment 1, five red-footed tortoises were trained to distinguish between food and non-food objects using a two-alternative forced choice procedure. After reaching criterion, they were presented with test trials in which the real objects were replaced with color photographs of those objects. There was no difference in performance between training and test trials, suggesting that the tortoises did see some correspondence between the real object and its photographic representation. Experiment 2 examined the nature of this correspondence by presenting the tortoises with a choice between the real food object and a photograph of it. The findings revealed that the tortoises confused the photograph with the real-life object. This suggests that they process real items and photographic representations of these items in the same way and, in this context, do not exhibit representational insight.

  7. Long-term visual object recognition memory in aged rats.

    PubMed

    Platano, Daniela; Fattoretti, Patrizia; Balietti, Marta; Bertoni-Freddari, Carlo; Aicardi, Giorgio

    2008-04-01

    Aging is associated with memory impairments, but the neural bases of this process need to be clarified. To this end, behavioral protocols for memory testing may be applied to aged animals to compare memory performances with functional and structural characteristics of specific brain regions. Visual object recognition memory can be investigated in the rat using a behavioral task based on its spontaneous preference for exploring novel rather than familiar objects. We found that a behavioral task able to elicit long-term visual object recognition memory in adult Long-Evans rats failed in aged (25-27 months old) Wistar rats. Since no tasks effective in aged rats are reported in the literature, we changed the experimental conditions to improve consolidation processes to assess whether this form of memory can still be maintained for long term at this age: the learning trials were performed in a smaller box, identical to the home cage, and the inter-trial delays were shortened. We observed a reduction in anxiety in this box (as indicated by the lower number of fecal boli produced during habituation), and we developed a learning protocol able to elicit a visual object recognition memory that was maintained after 24 h in these aged rats. When we applied the same protocol to adult rats, we obtained similar results. This experimental approach can be useful to study functional and structural changes associated with age-related memory impairments, and may help to identify new behavioral strategies and molecular targets that can be addressed to ameliorate memory performances during aging.

  8. GAYE: a face recognition system

    NASA Astrophysics Data System (ADS)

    Kepenekci, Burcu; Tek, F. Boray; Cilingir, Onur; Sakarya, Ufuk; Akar, Gozde B.

    2004-05-01

    In this paper, a new face recognition system, GAYE, is presented. GAYE is a fully automatic system that detects and recognizes faces in cluttered scenes. The input of the system is any digitized image/image sequence that includes face/faces. The basic building blocks of the system are face detection, feature extraction and feature comparison. Face detection is based on skin color segmentation. For feature extraction, a novel approach is proposed that depends on the Gabor wavelet transform of the face image. By comparing facial feature vectors system finally makes a decision if the incoming person is recognized or not. Real time system tests show that GAYE achieves a recognition ratio over %90.

  9. The Army word recognition system

    NASA Technical Reports Server (NTRS)

    Hadden, David R.; Haratz, David

    1977-01-01

    The application of speech recognition technology in the Army command and control area is presented. The problems associated with this program are described as well as as its relevance in terms of the man/machine interactions, voice inflexions, and the amount of training needed to interact with and utilize the automated system.

  10. Object recognition in clutter: cortical responses depend on the type of learning

    PubMed Central

    Hegdé, Jay; Thompson, Serena K.; Brady, Mark; Kersten, Daniel

    2012-01-01

    Theoretical studies suggest that the visual system uses prior knowledge of visual objects to recognize them in visual clutter, and posit that the strategies for recognizing objects in clutter may differ depending on whether or not the object was learned in clutter to begin with. We tested this hypothesis using functional magnetic resonance imaging (fMRI) of human subjects. We trained subjects to recognize naturalistic, yet novel objects in strong or weak clutter. We then tested subjects' recognition performance for both sets of objects in strong clutter. We found many brain regions that were differentially responsive to objects during object recognition depending on whether they were learned in strong or weak clutter. In particular, the responses of the left fusiform gyrus (FG) reliably reflected, on a trial-to-trial basis, subjects' object recognition performance for objects learned in the presence of strong clutter. These results indicate that the visual system does not use a single, general-purpose mechanism to cope with clutter. Instead, there are two distinct spatial patterns of activation whose responses are attributable not to the visual context in which the objects were seen, but to the context in which the objects were learned. PMID:22723774

  11. Canonical Wnt signaling is necessary for object recognition memory consolidation.

    PubMed

    Fortress, Ashley M; Schram, Sarah L; Tuscher, Jennifer J; Frick, Karyn M

    2013-07-31

    Wnt signaling has emerged as a potent regulator of hippocampal synaptic function, although no evidence yet supports a critical role for Wnt signaling in hippocampal memory. Here, we sought to determine whether canonical β-catenin-dependent Wnt signaling is necessary for hippocampal memory consolidation. Immediately after training in a hippocampal-dependent object recognition task, mice received a dorsal hippocampal (DH) infusion of vehicle or the canonical Wnt antagonist Dickkopf-1 (Dkk-1; 50, 100, or 200 ng/hemisphere). Twenty-four hours later, mice receiving vehicle remembered the familiar object explored during training. However, mice receiving Dkk-1 exhibited no memory for the training object, indicating that object recognition memory consolidation is dependent on canonical Wnt signaling. To determine how Dkk-1 affects canonical Wnt signaling, mice were infused with vehicle or 50 ng/hemisphere Dkk-1 and protein levels of Wnt-related proteins (Dkk-1, GSK3β, β-catenin, TCF1, LEF1, Cyclin D1, c-myc, Wnt7a, Wnt1, and PSD95) were measured in the dorsal hippocampus 5 min or 4 h later. Dkk-1 produced a rapid increase in Dkk-1 protein levels and a decrease in phosphorylated GSK3β levels, followed by a decrease in β-catenin, TCF1, LEF1, Cyclin D1, c-myc, Wnt7a, and PSD95 protein levels 4 h later. These data suggest that alterations in Wnt/GSK3β/β-catenin signaling may underlie the memory impairments induced by Dkk-1. In a subsequent experiment, object training alone rapidly increased DH GSK3β phosphorylation and levels of β-catenin and Cyclin D1. These data suggest that canonical Wnt signaling is regulated by object learning and is necessary for hippocampal memory consolidation.

  12. Are Face and Object Recognition Independent? A Neurocomputational Modeling Exploration.

    PubMed

    Wang, Panqu; Gauthier, Isabel; Cottrell, Garrison

    2016-04-01

    Are face and object recognition abilities independent? Although it is commonly believed that they are, Gauthier et al. [Gauthier, I., McGugin, R. W., Richler, J. J., Herzmann, G., Speegle, M., & VanGulick, A. E. Experience moderates overlap between object and face recognition, suggesting a common ability. Journal of Vision, 14, 7, 2014] recently showed that these abilities become more correlated as experience with nonface categories increases. They argued that there is a single underlying visual ability, v, that is expressed in performance with both face and nonface categories as experience grows. Using the Cambridge Face Memory Test and the Vanderbilt Expertise Test, they showed that the shared variance between Cambridge Face Memory Test and Vanderbilt Expertise Test performance increases monotonically as experience increases. Here, we address why a shared resource across different visual domains does not lead to competition and to an inverse correlation in abilities? We explain this conundrum using our neurocomputational model of face and object processing ["The Model", TM, Cottrell, G. W., & Hsiao, J. H. Neurocomputational models of face processing. In A. J. Calder, G. Rhodes, M. Johnson, & J. Haxby (Eds.), The Oxford handbook of face perception. Oxford, UK: Oxford University Press, 2011]. We model the domain general ability v as the available computational resources (number of hidden units) in the mapping from input to label and experience as the frequency of individual exemplars in an object category appearing during network training. Our results show that, as in the behavioral data, the correlation between subordinate level face and object recognition accuracy increases as experience grows. We suggest that different domains do not compete for resources because the relevant features are shared between faces and objects. The essential power of experience is to generate a "spreading transform" for faces (separating them in representational space) that

  13. Detailed 3D representations for object recognition and modeling.

    PubMed

    Zia, M Zeeshan; Stark, Michael; Schiele, Bernt; Schindler, Konrad

    2013-11-01

    Geometric 3D reasoning at the level of objects has received renewed attention recently in the context of visual scene understanding. The level of geometric detail, however, is typically limited to qualitative representations or coarse boxes. This is linked to the fact that today's object class detectors are tuned toward robust 2D matching rather than accurate 3D geometry, encouraged by bounding-box-based benchmarks such as Pascal VOC. In this paper, we revisit ideas from the early days of computer vision, namely, detailed, 3D geometric object class representations for recognition. These representations can recover geometrically far more accurate object hypotheses than just bounding boxes, including continuous estimates of object pose and 3D wireframes with relative 3D positions of object parts. In combination with robust techniques for shape description and inference, we outperform state-of-the-art results in monocular 3D pose estimation. In a series of experiments, we analyze our approach in detail and demonstrate novel applications enabled by such an object class representation, such as fine-grained categorization of cars and bicycles, according to their 3D geometry, and ultrawide baseline matching.

  14. Combat Systems Department Employee Recognition System

    DTIC Science & Technology

    1996-08-01

    the individual’s view of positive reinforcement . Include them in discussions. Ask for their opinions. 4 NSWCDD/MP-96/137 SECTION 3 INSTRUCTIONS 3.1...PROVIDES POSITIVE REINFORCEMENT . THE EASIER IT IS TO DO, THE MORE LIKELY IT IS TO GET DONE. N-DEPARTMENT EMPLOYEE RECOGNITION SYSTEM PRI NCI PLES THERE ARE...INDIVIDUAL’S VIEW OF POSITIVE REINFORCEMENT . ASK THEM I Papa .18Iv 15 N-DEPARTMENT EMPLOYEE RECOGNITION SYSTEM * OUTLINE A. TASK FORCE MEMBERSHIP

  15. Neural Substrates of View-Invariant Object Recognition Developed without Experiencing Rotations of the Objects

    PubMed Central

    Okamura, Jun-ya; Yamaguchi, Reona; Honda, Kazunari; Tanaka, Keiji

    2014-01-01

    One fails to recognize an unfamiliar object across changes in viewing angle when it must be discriminated from similar distractor objects. View-invariant recognition gradually develops as the viewer repeatedly sees the objects in rotation. It is assumed that different views of each object are associated with one another while their successive appearance is experienced in rotation. However, natural experience of objects also contains ample opportunities to discriminate among objects at each of the multiple viewing angles. Our previous behavioral experiments showed that after experiencing a new set of object stimuli during a task that required only discrimination at each of four viewing angles at 30° intervals, monkeys could recognize the objects across changes in viewing angle up to 60°. By recording activities of neurons from the inferotemporal cortex after various types of preparatory experience, we here found a possible neural substrate for the monkeys' performance. For object sets that the monkeys had experienced during the task that required only discrimination at each of four viewing angles, many inferotemporal neurons showed object selectivity covering multiple views. The degree of view generalization found for these object sets was similar to that found for stimulus sets with which the monkeys had been trained to conduct view-invariant recognition. These results suggest that the experience of discriminating new objects in each of several viewing angles develops the partially view-generalized object selectivity distributed over many neurons in the inferotemporal cortex, which in turn bases the monkeys' emergent capability to discriminate the objects across changes in viewing angle. PMID:25378169

  16. Neural substrates of view-invariant object recognition developed without experiencing rotations of the objects.

    PubMed

    Okamura, Jun-Ya; Yamaguchi, Reona; Honda, Kazunari; Wang, Gang; Tanaka, Keiji

    2014-11-05

    One fails to recognize an unfamiliar object across changes in viewing angle when it must be discriminated from similar distractor objects. View-invariant recognition gradually develops as the viewer repeatedly sees the objects in rotation. It is assumed that different views of each object are associated with one another while their successive appearance is experienced in rotation. However, natural experience of objects also contains ample opportunities to discriminate among objects at each of the multiple viewing angles. Our previous behavioral experiments showed that after experiencing a new set of object stimuli during a task that required only discrimination at each of four viewing angles at 30° intervals, monkeys could recognize the objects across changes in viewing angle up to 60°. By recording activities of neurons from the inferotemporal cortex after various types of preparatory experience, we here found a possible neural substrate for the monkeys' performance. For object sets that the monkeys had experienced during the task that required only discrimination at each of four viewing angles, many inferotemporal neurons showed object selectivity covering multiple views. The degree of view generalization found for these object sets was similar to that found for stimulus sets with which the monkeys had been trained to conduct view-invariant recognition. These results suggest that the experience of discriminating new objects in each of several viewing angles develops the partially view-generalized object selectivity distributed over many neurons in the inferotemporal cortex, which in turn bases the monkeys' emergent capability to discriminate the objects across changes in viewing angle.

  17. Recognition of similar objects using simulated prosthetic vision.

    PubMed

    Hu, Jie; Xia, Peng; Gu, Chaochen; Qi, Jin; Li, Sheng; Peng, Yinghong

    2014-02-01

    Due to the limitations of existing techniques, even the most advanced visual prostheses, using several hundred electrodes to transmit signals to the visual pathway, restrict sensory function and visual information. To identify the bottlenecks and guide prosthesis designing, psychophysics simulations of a visual prosthesis in normally sighted individuals are desirable. In this study, psychophysical experiments of discriminating objects with similar profiles were used to test the effects of phosphene array parameters (spatial resolution, gray scale, distortion, and dropout rate) on visual information using simulated prosthetic vision. The results showed that the increase in spatial resolution and number of gray levels and the decrease in phosphene distortion and dropout rate improved recognition performance, and the accuracy is 78.5% under the optimum condition (resolution: 32 × 32, gray level: 8, distortion: k = 0, dropout: 0%). In combined parameter tests, significant facial recognition accuracy was achieved for all the images with k = 0.1 distortion and 10% dropout. Compared with other experiments, we find that different objects do not show specific sensitivity to the changes of parameters and visual information is not nearly enough even under the optimum condition. The results suggests that higher spatial resolution and more gray levels are required for visual prosthetic devices and further research on image processing strategies to improve prosthetic vision is necessary, especially when the wearers have to accomplish more than simple visual tasks.

  18. Vision: are models of object recognition catching up with the brain?

    PubMed

    Poggio, Tomaso; Ullman, Shimon

    2013-12-01

    Object recognition has been a central yet elusive goal of computational vision. For many years, computer performance seemed highly deficient and unable to emulate the basic capabilities of the human recognition system. Over the past decade or so, computer scientists and neuroscientists have developed algorithms and systems-and models of visual cortex-that have come much closer to human performance in visual identification and categorization. In this personal perspective, we discuss the ongoing struggle of visual models to catch up with the visual cortex, identify key reasons for the relatively rapid improvement of artificial systems and models, and identify open problems for computational vision in this domain.

  19. Regularity Detection As A Strategy In Object Modelling And Recognition

    NASA Astrophysics Data System (ADS)

    van Gool, Luc J.; Wagemans, Johan; Oosterlinck, Andre J.

    1989-03-01

    Human subjects easily perceive and extensively use shape regularities such as symmetry or periodicity when they are confronted with the task of object description and recognition. A computer vision algorithm is presented which emulates such behaviour in that it similarly makes use of shape redundancies for the concise description and meaningful segmentation of object contours. This can be compared with the way in which designers proceed in using CAD/CAM. In order to make the problem more accessible to computer programming, the contours are analyzed in so-called 'arc length space'. This novel mapping facilitates the detection and elimination of regularities under a broad range of viewing conditions and yields a natural basis for the formulation of the corresponding model compression rules. Several of the regularities which have traditionally been treated separately, are given a unified substrate.

  20. Moment invariants applied to the recognition of objects using neural networks

    NASA Astrophysics Data System (ADS)

    Gonzaga, Adilson; Ferreira Costa, Jose A.

    1996-11-01

    Visual pattern recognition and visual object recognition are central aspects of high level computer vision systems. This paper describes a method of recognizing patterns and objects in digital images with several types of objects in different positions. The moment invariants of such real work, noise containing images are processed by a neural network, which performs a pattern classification. Two learning methods are adopted for training the network: the conjugate gradient and the Levenber-Maquardt algorithms, both in conjunction with simulated annealing, for different sets of error conditions and features. Real images are used for testing the net's correct class assignments and rejections. We present results and comments focusing on the system's capacity to generalize, even in the presence of noise, geometrical transformations, object shadows and other types of image degradation. One advantage of the artificial neural network employed is its low execution time, allowing the system to be integrated to an assembly industry line for automated visual inspection.

  1. Modeling 4D Human-Object Interactions for Joint Event Segmentation, Recognition, and Object Localization.

    PubMed

    Wei, Ping; Zhao, Yibiao; Zheng, Nanning; Zhu, Song-Chun

    2016-06-01

    In this paper, we present a 4D human-object interaction (4DHOI) model for solving three vision tasks jointly: i) event segmentation from a video sequence, ii) event recognition and parsing, and iii) contextual object localization. The 4DHOI model represents the geometric, temporal, and semantic relations in daily events involving human-object interactions. In 3D space, the interactions of human poses and contextual objects are modeled by semantic co-occurrence and geometric compatibility. On the time axis, the interactions are represented as a sequence of atomic event transitions with coherent objects. The 4DHOI model is a hierarchical spatial-temporal graph representation which can be used for inferring scene functionality and object affordance. The graph structures and parameters are learned using an ordered expectation maximization algorithm which mines the spatial-temporal structures of events from RGB-D video samples. Given an input RGB-D video, the inference is performed by a dynamic programming beam search algorithm which simultaneously carries out event segmentation, recognition, and object localization. We collected and released a large multiview RGB-D event dataset which contains 3,815 video sequences and 383,036 RGB-D frames captured by three RGB-D cameras. The experimental results on three challenging datasets demonstrate the strength of the proposed method.

  2. Category Specificity in Normal Episodic Learning: Applications to Object Recognition and Category-Specific Agnosia

    ERIC Educational Resources Information Center

    Bukach, Cindy M.; Bub, Daniel N.; Masson, Michael E. J.; Lindsay, D. Stephen

    2004-01-01

    Studies of patients with category-specific agnosia (CSA) have given rise to multiple theories of object recognition, most of which assume the existence of a stable, abstract semantic memory system. We applied an episodic view of memory to questions raised by CSA in a series of studies examining normal observers' recall of newly learned attributes…

  3. Category Specificity in Normal Episodic Learning: Applications to Object Recognition and Category-Specific Agnosia

    ERIC Educational Resources Information Center

    Bukach, Cindy M.; Bub, Daniel N.; Masson, Michael E. J.; Lindsay, D. Stephen

    2004-01-01

    Studies of patients with category-specific agnosia (CSA) have given rise to multiple theories of object recognition, most of which assume the existence of a stable, abstract semantic memory system. We applied an episodic view of memory to questions raised by CSA in a series of studies examining normal observers' recall of newly learned attributes…

  4. Short-term plasticity of visuo-haptic object recognition.

    PubMed

    Kassuba, Tanja; Klinge, Corinna; Hölig, Cordula; Röder, Brigitte; Siebner, Hartwig R

    2014-01-01

    Functional magnetic resonance imaging (fMRI) studies have provided ample evidence for the involvement of the lateral occipital cortex (LO), fusiform gyrus (FG), and intraparietal sulcus (IPS) in visuo-haptic object integration. Here we applied 30 min of sham (non-effective) or real offline 1 Hz repetitive transcranial magnetic stimulation (rTMS) to perturb neural processing in left LO immediately before subjects performed a visuo-haptic delayed-match-to-sample task during fMRI. In this task, subjects had to match sample (S1) and target (S2) objects presented sequentially within or across vision and/or haptics in both directions (visual-haptic or haptic-visual) and decide whether or not S1 and S2 were the same objects. Real rTMS transiently decreased activity at the site of stimulation and remote regions such as the right LO and bilateral FG during haptic S1 processing. Without affecting behavior, the same stimulation gave rise to relative increases in activation during S2 processing in the right LO, left FG, bilateral IPS, and other regions previously associated with object recognition. Critically, the modality of S2 determined which regions were recruited after rTMS. Relative to sham rTMS, real rTMS induced increased activations during crossmodal congruent matching in the left FG for haptic S2 and the temporal pole for visual S2. In addition, we found stronger activations for incongruent than congruent matching in the right anterior parahippocampus and middle frontal gyrus for crossmodal matching of haptic S2 and in the left FG and bilateral IPS for unimodal matching of visual S2, only after real but not sham rTMS. The results imply that a focal perturbation of the left LO triggers modality-specific interactions between the stimulated left LO and other key regions of object processing possibly to maintain unimpaired object recognition. This suggests that visual and haptic processing engage partially distinct brain networks during visuo-haptic object matching.

  5. Robust feature detection for 3D object recognition and matching

    NASA Astrophysics Data System (ADS)

    Pankanti, Sharath; Dorai, Chitra; Jain, Anil K.

    1993-06-01

    Salient surface features play a central role in tasks related to 3-D object recognition and matching. There is a large body of psychophysical evidence demonstrating the perceptual significance of surface features such as local minima of principal curvatures in the decomposition of objects into a hierarchy of parts. Many recognition strategies employed in machine vision also directly use features derived from surface properties for matching. Hence, it is important to develop techniques that detect surface features reliably. Our proposed scheme consists of (1) a preprocessing stage, (2) a feature detection stage, and (3) a feature integration stage. The preprocessing step selectively smoothes out noise in the depth data without degrading salient surface details and permits reliable local estimation of the surface features. The feature detection stage detects both edge-based and region-based features, of which many are derived from curvature estimates. The third stage is responsible for integrating the information provided by the individual feature detectors. This stage also completes the partial boundaries provided by the individual feature detectors, using proximity and continuity principles of Gestalt. All our algorithms use local support and, therefore, are inherently parallelizable. We demonstrate the efficacy and robustness of our approach by applying it to two diverse domains of applications: (1) segmentation of objects into volumetric primitives and (2) detection of salient contours on free-form surfaces. We have tested our algorithms on a number of real range images with varying degrees of noise and missing data due to self-occlusion. The preliminary results are very encouraging.

  6. Expanded Dempster-Shafer reasoning technique for image feature integration and object recognition

    NASA Astrophysics Data System (ADS)

    Zhu, Quiming; Huang, Yinghua; Payne, Matt G.

    1992-12-01

    Integration of information from multiple sources has been one of the key steps to the success of general vision systems. It is also an essential problem to the development of color image understanding algorithms that make full use of the multichannel color data for object recognition. This paper presents a feature integration system characterized by a hybrid combination of a statistic-based reasoning technique and a symbolic logic-based inference method. A competitive evidence enhancement scheme is used in the process to fuse information from multiple sources. The scheme expands the Dempster-Shafer's function of combination and improves the reliability of the object recognition. When applied to integrate the object features extracted from the multiple spectra of the color images, the system alleviates the drawback of traditional Baysian classification system.

  7. Object recognition testing: methodological considerations on exploration and discrimination measures.

    PubMed

    Akkerman, Sven; Blokland, Arjan; Reneerkens, Olga; van Goethem, Nick P; Bollen, Eva; Gijselaers, Hieronymus J M; Lieben, Cindy K J; Steinbusch, Harry W M; Prickaerts, Jos

    2012-07-01

    The object recognition task (ORT) is a popular one-trial learning test for animals. In the current study, we investigated several methodological issues concerning the task. Data was pooled from 28 ORT studies, containing 731 male Wistar rats. We investigated the relationship between 3 common absolute- and relative discrimination measures, as well as their relation to exploratory activity. In this context, the effects of pre-experimental habituation, object familiarity, trial duration, retention interval and the amnesic drugs MK-801 and scopolamine were investigated. Our analyses showed that the ORT is very sensitive, capable of detecting subtle differences in memory (discrimination) and exploratory performance. As a consequence, it is susceptible to potential biases due to (injection) stress and side effects of drugs. Our data indicated that a minimum amount of exploration is required in the sample and test trial for stable significant discrimination performance. However, there was no relationship between the level of exploration in the sample trial and discrimination performance. In addition, the level of exploration in the test trial was positively related to the absolute discrimination measure, whereas this was not the case for relative discrimination measures, which correct for exploratory differences, making them more resistant to exploration biases. Animals appeared to remember object information over multiple test sessions. Therefore, when animals have encountered both objects in prior test sessions, the object preference observed in the test trial of 1h retention intervals is probably due to a relative difference in familiarity between the objects in the test trial, rather than true novelty per se. Taken together, our findings suggest to take into consideration pre-experimental exposure (familiarization) to objects, habituation to treatment procedures, and the use of relative discrimination measures when using the ORT.

  8. Plastic modifications induced by object recognition memory processing

    PubMed Central

    Clarke, Julia Rosauro; Cammarota, Martín; Gruart, Agnès; Izquierdo, Iván; Delgado-García, José María

    2010-01-01

    Long-term potentiation (LTP) phenomenon is widely accepted as a cellular model of memory consolidation. Object recognition (OR) is a particularly useful way of studying declarative memory in rodents because it makes use of their innate preference for novel over familiar objects. In this study, mice had electrodes implanted in the hippocampal Schaffer collaterals–pyramidal CA1 pathway and were trained for OR. Field EPSPs evoked at the CA3-CA1 synapse were recorded at the moment of training and at different times thereafter. LTP-like synaptic enhancement was found 6 h posttraining. A testing session was conducted 24 h after training, in the presence of one familiar and one novel object. Hippocampal synaptic facilitation was observed during exploration of familiar and novel objects. A short depotentiation period was observed early after the test and was followed by a later phase of synaptic efficacy enhancement. Here, we show that OR memory consolidation is accompanied by transient potentiation in the hippocampal CA3-CA1 synapses, while reconsolidation of this memory requires a short-lasting phase of depotentiation that could account for its well described vulnerability. The late synaptic enhancement phase, on the other hand, would be a consequence of memory restabilization. PMID:20133798

  9. Combining feature- and correspondence-based methods for visual object recognition.

    PubMed

    Westphal, Günter; Würtz, Rolf P

    2009-07-01

    We present an object recognition system built on a combination of feature- and correspondence-based pattern recognizers. The feature-based part, called preselection network, is a single-layer feedforward network weighted with the amount of information contributed by each feature to the decision at hand. For processing arbitrary objects, we employ small, regular graphs whose nodes are attributed with Gabor amplitudes, termed parquet graphs. The preselection network can quickly rule out most irrelevant matches and leaves only the ambiguous cases, so-called model candidates, to be verified by a rudimentary version of elastic graph matching, a standard correspondence-based technique for face and object recognition. According to the model, graphs are constructed that describe the object in the input image well. We report the results of experiments on standard databases for object recognition. The method achieved high recognition rates on identity and pose. Unlike many other models, it can also cope with varying background, multiple objects, and partial occlusion.

  10. Laptop Computer - Based Facial Recognition System Assessment

    SciTech Connect

    R. A. Cain; G. B. Singleton

    2001-03-01

    The objective of this project was to assess the performance of the leading commercial-off-the-shelf (COTS) facial recognition software package when used as a laptop application. We performed the assessment to determine the system's usefulness for enrolling facial images in a database from remote locations and conducting real-time searches against a database of previously enrolled images. The assessment involved creating a database of 40 images and conducting 2 series of tests to determine the product's ability to recognize and match subject faces under varying conditions. This report describes the test results and includes a description of the factors affecting the results. After an extensive market survey, we selected Visionics' FaceIt{reg_sign} software package for evaluation and a review of the Facial Recognition Vendor Test 2000 (FRVT 2000). This test was co-sponsored by the US Department of Defense (DOD) Counterdrug Technology Development Program Office, the National Institute of Justice, and the Defense Advanced Research Projects Agency (DARPA). Administered in May-June 2000, the FRVT 2000 assessed the capabilities of facial recognition systems that were currently available for purchase on the US market. Our selection of this Visionics product does not indicate that it is the ''best'' facial recognition software package for all uses. It was the most appropriate package based on the specific applications and requirements for this specific application. In this assessment, the system configuration was evaluated for effectiveness in identifying individuals by searching for facial images captured from video displays against those stored in a facial image database. An additional criterion was that the system be capable of operating discretely. For this application, an operational facial recognition system would consist of one central computer hosting the master image database with multiple standalone systems configured with duplicates of the master operating in

  11. Exploring local regularities for 3D object recognition

    NASA Astrophysics Data System (ADS)

    Tian, Huaiwen; Qin, Shengfeng

    2016-11-01

    In order to find better simplicity measurements for 3D object recognition, a new set of local regularities is developed and tested in a stepwise 3D reconstruction method, including localized minimizing standard deviation of angles(L-MSDA), localized minimizing standard deviation of segment magnitudes(L-MSDSM), localized minimum standard deviation of areas of child faces (L-MSDAF), localized minimum sum of segment magnitudes of common edges (L-MSSM), and localized minimum sum of areas of child face (L-MSAF). Based on their effectiveness measurements in terms of form and size distortions, it is found that when two local regularities: L-MSDA and L-MSDSM are combined together, they can produce better performance. In addition, the best weightings for them to work together are identified as 10% for L-MSDSM and 90% for L-MSDA. The test results show that the combined usage of L-MSDA and L-MSDSM with identified weightings has a potential to be applied in other optimization based 3D recognition methods to improve their efficacy and robustness.

  12. Moving Object Control System

    NASA Technical Reports Server (NTRS)

    Arndt, G. Dickey (Inventor); Carl, James R. (Inventor)

    2001-01-01

    A method is provided for controlling two objects relatively moveable with respect to each other. A plurality of receivers are provided for detecting a distinctive microwave signal from each of the objects and measuring the phase thereof with respect to a reference signal. The measured phase signal is used to determine a distance between each of the objects and each of the plurality of receivers. Control signals produced in response to the relative distances are used to control the position of the two objects.

  13. Anthropomorphic robot for recognition and drawing generalized object images

    NASA Astrophysics Data System (ADS)

    Ginzburg, Vera M.

    1998-10-01

    The process of recognition, for instance, understanding the text, written by different fonts, consists in the depriving of the individual attributes of the letters in the particular font. It is shown that such process, in Nature and technique, can be provided by the narrowing the spatial frequency of the object's image by its defocusing. In defocusing images remain only areas, so-called Informative Fragments (IFs), which all together form the generalized (stylized) image of many identical objects. It is shown that the variety of shapes of IFs is restricted and can be presented by `Geometrical alphabet'. The `letters' for this alphabet can be created using two basic `genetic' figures: a stripe and round spot. It is known from physiology that the special cells of visual cortex response to these particular figures. The prototype of such `genetic' alphabet has been made using Boolean algebra (Venn's diagrams). The algorithm for drawing the letter's (`genlet's') shape in this alphabet and generalized images of objects (for example, `sleeping cat'), are given. A scheme of an anthropomorphic robot is shown together with results of model computer experiment of the robot's action--`drawing' the generalized image.

  14. Organization of face and object recognition in modular neural network models.

    PubMed

    Dailey, M N.; Cottrell, G W.

    1999-10-01

    There is strong evidence that face processing in the brain is localized. The double dissociation between prosopagnosia, a face recognition deficit occurring after brain damage, and visual object agnosia, difficulty recognizing other kinds of complex objects, indicates that face and non-face object recognition may be served by partially independent neural mechanisms. In this paper, we use computational models to show how the face processing specialization apparently underlying prosopagnosia and visual object agnosia could be attributed to (1) a relatively simple competitive selection mechanism that, during development, devotes neural resources to the tasks they are best at performing, (2) the developing infant's need to perform subordinate classification (identification) of faces early on, and (3) the infant's low visual acuity at birth. Inspired by de Schonen, Mancini and Liegeois' arguments (1998) [de Schonen, S., Mancini, J., Liegeois, F. (1998). About functional cortical specialization: the development of face recognition. In: F. Simon & G. Butterworth, The development of sensory, motor, and cognitive capacities in early infancy (pp. 103-116). Hove, UK: Psychology Press] that factors like these could bias the visual system to develop a processing subsystem particularly useful for face recognition, and Jacobs and Kosslyn's experiments (1994) [Jacobs, R. A., & Kosslyn, S. M. (1994). Encoding shape and spatial relations-the role of receptive field size in coordination complementary representations. Cognitive Science, 18(3), 361-368] in the mixtures of experts (ME) modeling paradigm, we provide a preliminary computational demonstration of how this theory accounts for the double dissociation between face and object processing. We present two feed-forward computational models of visual processing. In both models, the selection mechanism is a gating network that mediates a competition between modules attempting to classify input stimuli. In Model I, when the modules

  15. When Action Observation Facilitates Visual Perception: Activation in Visuo-Motor Areas Contributes to Object Recognition.

    PubMed

    Sim, Eun-Jin; Helbig, Hannah B; Graf, Markus; Kiefer, Markus

    2015-09-01

    Recent evidence suggests an interaction between the ventral visual-perceptual and dorsal visuo-motor brain systems during the course of object recognition. However, the precise function of the dorsal stream for perception remains to be determined. The present study specified the functional contribution of the visuo-motor system to visual object recognition using functional magnetic resonance imaging and event-related potential (ERP) during action priming. Primes were movies showing hands performing an action with an object with the object being erased, followed by a manipulable target object, which either afforded a similar or a dissimilar action (congruent vs. incongruent condition). Participants had to recognize the target object within a picture-word matching task. Priming-related reductions of brain activity were found in frontal and parietal visuo-motor areas as well as in ventral regions including inferior and anterior temporal areas. Effective connectivity analyses suggested functional influences of parietal areas on anterior temporal areas. ERPs revealed priming-related source activity in visuo-motor regions at about 120 ms and later activity in the ventral stream at about 380 ms. Hence, rapidly initiated visuo-motor processes within the dorsal stream functionally contribute to visual object recognition in interaction with ventral stream processes dedicated to visual analysis and semantic integration.

  16. Infrared detection, recognition and identification of handheld objects

    NASA Astrophysics Data System (ADS)

    Adomeit, Uwe

    2012-10-01

    A main criterion for comparison and selection of thermal imagers for military applications is their nominal range performance. This nominal range performance is calculated for a defined task and standardized target and environmental conditions. The only standardization available to date is STANAG 4347. The target defined there is based on a main battle tank in front view. Because of modified military requirements, this target is no longer up-to-date. Today, different topics of interest are of interest, especially differentiation between friend and foe and identification of humans. There is no direct way to differentiate between friend and foe in asymmetric scenarios, but one clue can be that someone is carrying a weapon. This clue can be transformed in the observer tasks detection: a person is carrying or is not carrying an object, recognition: the object is a long / medium / short range weapon or civil equipment and identification: the object can be named (e. g. AK-47, M-4, G36, RPG7, Axe, Shovel etc.). These tasks can be assessed experimentally and from the results of such an assessment, a standard target for handheld objects may be derived. For a first assessment, a human carrying 13 different handheld objects in front of his chest was recorded at four different ranges with an IR-dual-band camera. From the recorded data, a perception experiment was prepared. It was conducted with 17 observers in a 13-alternative forced choice, unlimited observation time arrangement. The results of the test together with Minimum Temperature Difference Perceived measurements of the camera and temperature difference and critical dimension derived from the recorded imagery allowed defining a first standard target according to the above tasks. This standard target consist of 2.5 / 3.5 / 5 DRI line pairs on target, 0.24 m critical size and 1 K temperature difference. The values are preliminary and have to be refined in the future. Necessary are different aspect angles, different

  17. The role of histamine receptors in the consolidation of object recognition memory.

    PubMed

    da Silveira, Clarice Krás Borges; Furini, Cristiane R G; Benetti, Fernando; Monteiro, Siomara da Cruz; Izquierdo, Ivan

    2013-07-01

    Findings have shown that histamine receptors in the hippocampus modulate the acquisition and extinction of fear motivated learning. In order to determine the role of hippocampal histaminergic receptors on recognition memory, adult male Wistar rats with indwelling infusion cannulae stereotaxically placed in the CA1 region of dorsal hippocampus were trained in an object recognition learning task involving exposure to two different stimulus objects in an enclosed environment. In the test session, one of the objects presented during training was replaced by a novel one. Recognition memory retention was assessed 24 h after training by comparing the time spent in exploration (sniffing and touching) of the known object with that of the novel one. When infused in the CA1 region immediately, 30, 120 or 360 min posttraining, the H1-receptor antagonist, pyrilamine, the H2-receptor antagonist, ranitidine, and the H3-receptor agonist, imetit, blocked long-term memory retention in a time dependent manner (30-120 min) without affecting general exploratory behavior, anxiety state or hippocampal function. Our data indicate that histaminergic system modulates consolidation of object recognition memory through H1, H2 and H3 receptors.

  18. Severe Cross-Modal Object Recognition Deficits in Rats Treated Sub-Chronically with NMDA Receptor Antagonists are Reversed by Systemic Nicotine: Implications for Abnormal Multisensory Integration in Schizophrenia

    PubMed Central

    Jacklin, Derek L; Goel, Amit; Clementino, Kyle J; Hall, Alexander W M; Talpos, John C; Winters, Boyer D

    2012-01-01

    Schizophrenia is a complex and debilitating disorder, characterized by positive, negative, and cognitive symptoms. Among the cognitive deficits observed in patients with schizophrenia, recent work has indicated abnormalities in multisensory integration, a process that is important for the formation of comprehensive environmental percepts and for the appropriate guidance of behavior. Very little is known about the neural bases of such multisensory integration deficits, partly because of the lack of viable behavioral tasks to assess this process in animal models. In this study, we used our recently developed rodent cross-modal object recognition (CMOR) task to investigate multisensory integration functions in rats treated sub-chronically with one of two N-methyl-D-aspartate receptor (NMDAR) antagonists, MK-801, or ketamine; such treatment is known to produce schizophrenia-like symptoms. Rats treated with the NMDAR antagonists were impaired on the standard spontaneous object recognition (SOR) task, unimodal (tactile or visual only) versions of SOR, and the CMOR task with intermediate to long retention delays between acquisition and testing phases, but they displayed a selective CMOR task deficit when mnemonic demand was minimized. This selective impairment in multisensory information processing was dose-dependently reversed by acute systemic administration of nicotine. These findings suggest that persistent NMDAR hypofunction may contribute to the multisensory integration deficits observed in patients with schizophrenia and highlight the valuable potential of the CMOR task to facilitate further systematic investigation of the neural bases of, and potential treatments for, this hitherto overlooked aspect of cognitive dysfunction in schizophrenia. PMID:22669170

  19. The influence of color information on the recognition of color diagnostic and noncolor diagnostic objects.

    PubMed

    Bramão, Inês; Inácio, Filomena; Faísca, Luís; Reis, Alexandra; Petersson, Karl Magnus

    2011-01-01

    In the present study, the authors explore in detail the level of visual object recognition at which perceptual color information improves the recognition of color diagnostic and noncolor diagnostic objects. To address this issue, 3 object recognition tasks with different cognitive demands were designed: (a) an object verification task; (b) a category verification task; and (c) a name verification task. The authors found that perceptual color information improved color diagnostic object recognition mainly in tasks for which access to the semantic knowledge about the object was necessary to perform the task; that is, in category and name verification. In contrast, the authors found that perceptual color information facilitates noncolor diagnostic object recognition when access to the object's structural description from long-term memory was necessary--that is, object verification. In summary, the present study shows that the role of perceptual color information in object recognition is dependent on color diagnosticity.

  20. 3-D Object Recognition from Point Cloud Data

    NASA Astrophysics Data System (ADS)

    Smith, W.; Walker, A. S.; Zhang, B.

    2011-09-01

    The market for real-time 3-D mapping includes not only traditional geospatial applications but also navigation of unmanned autonomous vehicles (UAVs). Massively parallel processes such as graphics processing unit (GPU) computing make real-time 3-D object recognition and mapping achievable. Geospatial technologies such as digital photogrammetry and GIS offer advanced capabilities to produce 2-D and 3-D static maps using UAV data. The goal is to develop real-time UAV navigation through increased automation. It is challenging for a computer to identify a 3-D object such as a car, a tree or a house, yet automatic 3-D object recognition is essential to increasing the productivity of geospatial data such as 3-D city site models. In the past three decades, researchers have used radiometric properties to identify objects in digital imagery with limited success, because these properties vary considerably from image to image. Consequently, our team has developed software that recognizes certain types of 3-D objects within 3-D point clouds. Although our software is developed for modeling, simulation and visualization, it has the potential to be valuable in robotics and UAV applications. The locations and shapes of 3-D objects such as buildings and trees are easily recognizable by a human from a brief glance at a representation of a point cloud such as terrain-shaded relief. The algorithms to extract these objects have been developed and require only the point cloud and minimal human inputs such as a set of limits on building size and a request to turn on a squaring option. The algorithms use both digital surface model (DSM) and digital elevation model (DEM), so software has also been developed to derive the latter from the former. The process continues through the following steps: identify and group 3-D object points into regions; separate buildings and houses from trees; trace region boundaries; regularize and simplify boundary polygons; construct complex roofs. Several case

  1. Cascade fuzzy ART: a new extensible database for model-based object recognition

    NASA Astrophysics Data System (ADS)

    Hung, Hai-Lung; Liao, Hong-Yuan M.; Lin, Shing-Jong; Lin, Wei-Chung; Fan, Kuo-Chin

    1996-02-01

    In this paper, we propose a cascade fuzzy ART (CFART) neural network which can be used as an extensible database in a model-based object recognition system. The proposed CFART networks can accept both binary and continuous inputs. Besides, it preserves the prominent characteristics of a fuzzy ART network and extends the fuzzy ART's capability toward a hierarchical class representation of input patterns. The learning processes of the proposed network are unsupervised and self-organizing, which include coupled top-down searching and bottom-up learning processes. In addition, a global searching tree is built to speed up the learning and recognition processes.

  2. Image quality analysis and improvement of Ladar reflective tomography for space object recognition

    NASA Astrophysics Data System (ADS)

    Wang, Jin-cheng; Zhou, Shi-wei; Shi, Liang; Hu, Yi-Hua; Wang, Yong

    2016-01-01

    Some problems in the application of Ladar reflective tomography for space object recognition are studied in this work. An analytic target model is adopted to investigate the image reconstruction properties with limited relative angle range, which are useful to verify the target shape from the incomplete image, analyze the shadowing effect of the target and design the satellite payloads against recognition via reflective tomography approach. We proposed an iterative maximum likelihood method basing on Bayesian theory, which can effectively compress the pulse width and greatly improve the image resolution of incoherent LRT system without loss of signal to noise ratio.

  3. Emerging technologies with potential for objectively evaluating speech recognition skills.

    PubMed

    Rawool, Vishakha Waman

    2016-01-01

    Work-related exposure to noise and other ototoxins can cause damage to the cochlea, synapses between the inner hair cells, the auditory nerve fibers, and higher auditory pathways, leading to difficulties in recognizing speech. Procedures designed to determine speech recognition scores (SRS) in an objective manner can be helpful in disability compensation cases where the worker claims to have poor speech perception due to exposure to noise or ototoxins. Such measures can also be helpful in determining SRS in individuals who cannot provide reliable responses to speech stimuli, including patients with Alzheimer's disease, traumatic brain injuries, and infants with and without hearing loss. Cost-effective neural monitoring hardware and software is being rapidly refined due to the high demand for neurogaming (games involving the use of brain-computer interfaces), health, and other applications. More specifically, two related advances in neuro-technology include relative ease in recording neural activity and availability of sophisticated analysing techniques. These techniques are reviewed in the current article and their applications for developing objective SRS procedures are proposed. Issues related to neuroaudioethics (ethics related to collection of neural data evoked by auditory stimuli including speech) and neurosecurity (preservation of a person's neural mechanisms and free will) are also discussed.

  4. Object recognition in Williams syndrome: uneven ventral stream activation.

    PubMed

    O'Hearn, Kirsten; Roth, Jennifer K; Courtney, Susan M; Luna, Beatriz; Street, Whitney; Terwillinger, Robert; Landau, Barbara

    2011-05-01

    Williams syndrome (WS) is a genetic disorder associated with severe visuospatial deficits, relatively strong language skills, heightened social interest, and increased attention to faces. On the basis of the visuospatial deficits, this disorder has been characterized primarily as a deficit of the dorsal stream, the occipitoparietal brain regions that subserve visuospatial processing. However, some evidence indicates that this disorder may also affect the development of the ventral stream, the occipitotemporal cortical regions that subserve face and object recognition. The present studies examined ventral stream function in WS, with the hypothesis that faces would produce a relatively more mature pattern of ventral occipitotemporal activation, relative to other objects that are also represented across these visual areas. Using functional magnetic imaging, we compared activation patterns during viewing of human faces, cat faces, houses and shoes in individuals with WS (age 14-27), typically developing 6-9-year-olds (matched approximately on mental age), and typically developing 14-26-year-olds (matched on chronological age). Typically developing individuals exhibited changes in the pattern of activation over age, consistent with previous reports. The ventral stream topography of individuals with WS differed from both control groups, however, reflecting the same level of activation to face stimuli as chronological age matches, but less activation to house stimuli than either mental age or chronological age matches. We discuss the possible causes of this unusual topography and implications for understanding the behavioral profile of people with WS.

  5. Learning invariant object recognition from temporal correlation in a hierarchical network.

    PubMed

    Lessmann, Markus; Würtz, Rolf P

    2014-06-01

    Invariant object recognition, which means the recognition of object categories independent of conditions like viewing angle, scale and illumination, is a task of great interest that humans can fulfill much better than artificial systems. During the last years several basic principles were derived from neurophysiological observations and careful consideration: (1) Developing invariance to possible transformations of the object by learning temporal sequences of visual features that occur during the respective alterations. (2) Learning in a hierarchical structure, so basic level (visual) knowledge can be reused for different kinds of objects. (3) Using feedback to compare predicted input with the current one for choosing an interpretation in the case of ambiguous signals. In this paper we propose a network which implements all of these concepts in a computationally efficient manner which gives very good results on standard object datasets. By dynamically switching off weakly active neurons and pruning weights computation is sped up and thus handling of large databases with several thousands of images and a number of categories in a similar order becomes possible. The involved parameters allow flexible adaptation to the information content of training data and allow tuning to different databases relatively easily. Precondition for successful learning is that training images are presented in an order assuring that images of the same object under similar viewing conditions follow each other. Through an implementation with sparse data structures the system has moderate memory demands and still yields very good recognition rates.

  6. Real-time concealed-object detection and recognition with passive millimeter wave imaging.

    PubMed

    Yeom, Seokwon; Lee, Dong-Su; Jang, Yushin; Lee, Mun-Kyo; Jung, Sang-Won

    2012-04-23

    Millimeter wave (MMW) imaging is finding rapid adoption in security applications such as concealed object detection under clothing. A passive MMW imaging system can operate as a stand-off type sensor that scans people in both indoors and outdoors. However, the imaging system often suffers from the diffraction limit and the low signal level. Therefore, suitable intelligent image processing algorithms would be required for automatic detection and recognition of the concealed objects. This paper proposes real-time outdoor concealed-object detection and recognition with a radiometric imaging system. The concealed object region is extracted by the multi-level segmentation. A novel approach is proposed to measure similarity between two binary images. Principal component analysis (PCA) regularizes the shape in terms of translation and rotation. A geometric-based feature vector is composed of shape descriptors, which can achieve scale and orientation-invariant and distortion-tolerant property. Class is decided by minimum Euclidean distance between normalized feature vectors. Experiments confirm that the proposed methods provide fast and reliable recognition of the concealed object carried by a moving human subject.

  7. Cross-modal object recognition and dynamic weighting of sensory inputs in a fish

    PubMed Central

    Schumacher, Sarah; Burt de Perera, Theresa; Thenert, Johanna; von der Emde, Gerhard

    2016-01-01

    Most animals use multiple sensory modalities to obtain information about objects in their environment. There is a clear adaptive advantage to being able to recognize objects cross-modally and spontaneously (without prior training with the sense being tested) as this increases the flexibility of a multisensory system, allowing an animal to perceive its world more accurately and react to environmental changes more rapidly. So far, spontaneous cross-modal object recognition has only been shown in a few mammalian species, raising the question as to whether such a high-level function may be associated with complex mammalian brain structures, and therefore absent in animals lacking a cerebral cortex. Here we use an object-discrimination paradigm based on operant conditioning to show, for the first time to our knowledge, that a nonmammalian vertebrate, the weakly electric fish Gnathonemus petersii, is capable of performing spontaneous cross-modal object recognition and that the sensory inputs are weighted dynamically during this task. We found that fish trained to discriminate between two objects with either vision or the active electric sense, were subsequently able to accomplish the task using only the untrained sense. Furthermore we show that cross-modal object recognition is influenced by a dynamic weighting of the sensory inputs. The fish weight object-related sensory inputs according to their reliability, to minimize uncertainty and to enable an optimal integration of the senses. Our results show that spontaneous cross-modal object recognition and dynamic weighting of sensory inputs are present in a nonmammalian vertebrate. PMID:27313211

  8. Objective Color Measuring System

    DTIC Science & Technology

    1982-09-01

    F. W. Billmeyer , Jr., Comparative performance of color measuring instruments, Appl. Optics 8, 775-783 (1969). 3 F. W. Billmeyer , Jr., E. D. Campbell...comments, Appl. Optics 14, 265 (1975). 4 R. T. Marcus and F. W. Billmeyer , Jr., Statistical study of color-measurement instrumentation, Appl. Optics 13... Billmeyer , Jr. and P. J. Alessi, Assessment of color-manuring instruments for objective textile acceptability judgment, NATICK/TR-79/044, US Army Natick R

  9. Associative recognition and the hippocampus: differential effects of hippocampal lesions on object-place, object-context and object-place-context memory.

    PubMed

    Langston, Rosamund F; Wood, Emma R

    2010-10-01

    The hippocampus is thought to be required for the associative recognition of objects together with the spatial or temporal contexts in which they occur. However, recent data showing that rats with fornix lesions perform as well as controls in an object-place task, while being impaired on an object-place-context task (Eacott and Norman (2004) J Neurosci 24:1948-1953), suggest that not all forms of context-dependent associative recognition depend on the integrity of the hippocampus. To examine the role of the hippocampus in context-dependent recognition directly, the present study tested the effects of large, selective, bilateral hippocampus lesions in rats on performance of a series of spontaneous recognition memory tasks: object recognition, object-place recognition, object-context recognition and object-place-context recognition. Consistent with the effects of fornix lesions, animals with hippocampus lesions were impaired only on the object-place-context task. These data confirm that not all forms of context-dependent associative recognition are mediated by the hippocampus. Subsequent experiments suggested that the object-place task does not require an allocentric representation of space, which could account for the lack of impairment following hippocampus lesions. Importantly, as the object-place-context task has similar spatial requirements, the selective deficit in object-place-context recognition suggests that this task requires hippocampus-dependent neural processes distinct from those required for allocentric spatial memory, or for object memory, object-place memory or object-context memory. Two possibilities are that object, place, and context information converge only in the hippocampus, or that recognition of integrated object-place-context information requires a hippocampus-dependent mode of retrieval, such as recollection.

  10. A rodent model for the study of invariant visual object recognition.

    PubMed

    Zoccolan, Davide; Oertelt, Nadja; DiCarlo, James J; Cox, David D

    2009-05-26

    The human visual system is able to recognize objects despite tremendous variation in their appearance on the retina resulting from variation in view, size, lighting, etc. This ability--known as "invariant" object recognition--is central to visual perception, yet its computational underpinnings are poorly understood. Traditionally, nonhuman primates have been the animal model-of-choice for investigating the neuronal substrates of invariant recognition, because their visual systems closely mirror our own. Meanwhile, simpler and more accessible animal models such as rodents have been largely overlooked as possible models of higher-level visual functions, because their brains are often assumed to lack advanced visual processing machinery. As a result, little is known about rodents' ability to process complex visual stimuli in the face of real-world image variation. In the present work, we show that rats possess more advanced visual abilities than previously appreciated. Specifically, we trained pigmented rats to perform a visual task that required them to recognize objects despite substantial variation in their appearance, due to changes in size, view, and lighting. Critically, rats were able to spontaneously generalize to previously unseen transformations of learned objects. These results provide the first systematic evidence for invariant object recognition in rats and argue for an increased focus on rodents as models for studying high-level visual processing.

  11. The speed of object recognition from a haptic glance: event-related potential evidence.

    PubMed

    Gurtubay-Antolin, Ane; Rodriguez-Herreros, Borja; Rodríguez-Fornells, Antoni

    2015-05-01

    Recognition of an object usually involves a wide range of sensory inputs. Accumulating evidence shows that first brain responses associated with the visual discrimination of objects emerge around 150 ms, but fewer studies have been devoted to measure the first neural signature of haptic recognition. To investigate the speed of haptic processing, we recorded event-related potentials (ERPs) during a shape discrimination task without visual information. After a restricted exploratory procedure, participants (n = 27) were instructed to judge whether the touched object corresponded to an expected object whose name had been previously presented in a screen. We encountered that any incongruence between the presented word and the shape of the object evoked a frontocentral negativity starting at ∼175 ms. With the use of source analysis and L2 minimum-norm estimation, the neural sources of this differential activity were located in higher level somatosensory areas and prefrontal regions involved in error monitoring and cognitive control. Our findings reveal that the somatosensory system is able to complete an amount of haptic processing substantial enough to trigger conflict-related responses in medial and prefrontal cortices in <200 ms. The present results show that our haptic system is a fast recognition device closely interlinked with error- and conflict-monitoring processes.

  12. Generalization between canonical and non-canonical views in object recognition

    PubMed Central

    Ghose, Tandra; Liu, Zili

    2013-01-01

    Viewpoint generalization in object recognition is the process that allows recognition of a given 3D object from many different viewpoints despite variations in its 2D projections. We used the canonical view effects as a foundation to empirically test the validity of a major theory in object recognition, the view-approximation model (Poggio & Edelman, 1990). This model predicts that generalization should be better when an object is first seen from a non-canonical view and then a canonical view than when seen in the reversed order. We also manipulated object similarity to study the degree to which this view generalization was constrained by shape details and task instructions (object vs. image recognition). Old-new recognition performance for basic and subordinate level objects was measured in separate blocks. We found that for object recognition, view generalization between canonical and non-canonical views was comparable for basic level objects. For subordinate level objects, recognition performance was more accurate from non-canonical to canonical views than the other way around. When the task was changed from object recognition to image recognition, the pattern of the results reversed. Interestingly, participants responded “old” to “new” images of “old” objects with a substantially higher rate than to “new” objects, despite instructions to the contrary, thereby indicating involuntary view generalization. Our empirical findings are incompatible with the prediction of the view-approximation theory, and argue against the hypothesis that views are stored independently. PMID:23283692

  13. Measuring the Speed of Newborn Object Recognition in Controlled Visual Worlds

    ERIC Educational Resources Information Center

    Wood, Justin N.; Wood, Samantha M. W.

    2017-01-01

    How long does it take for a newborn to recognize an object? Adults can recognize objects rapidly, but measuring object recognition speed in newborns has not previously been possible. Here we introduce an automated controlled-rearing method for measuring the speed of newborn object recognition in controlled visual worlds. We raised newborn chicks…

  14. Communicative Signals Promote Object Recognition Memory and Modulate the Right Posterior STS.

    PubMed

    Redcay, Elizabeth; Ludlum, Ruth S; Velnoskey, Kayla R; Kanwal, Simren

    2016-01-01

    Detection of communicative signals is thought to facilitate knowledge acquisition early in life, but less is known about the role these signals play in adult learning or about the brain systems supporting sensitivity to communicative intent. The current study examined how ostensive gaze cues and communicative actions affect adult recognition memory and modulate neural activity as measured by fMRI. For both the behavioral and fMRI experiments, participants viewed a series of videos of an actress acting on one of two objects in front of her. Communicative context in the videos was manipulated in a 2 × 2 design in which the actress either had direct gaze (Gaze) or wore a visor (NoGaze) and either pointed at (Point) or reached for (Reach) one of the objects (target) in front of her. Participants then completed a recognition memory task with old (target and nontarget) objects and novel objects. Recognition memory for target objects in the Gaze conditions was greater than NoGaze, but no effects of gesture type were seen. Similarly, the fMRI video-viewing task revealed a significant effect of Gaze within right posterior STS (pSTS), but no significant effects of Gesture. Furthermore, pSTS sensitivity to Gaze conditions was related to greater memory for objects viewed in Gaze, as compared with NoGaze, conditions. Taken together, these results demonstrate that the ostensive, communicative signal of direct gaze preceding an object-directed action enhances recognition memory for attended items and modulates the pSTS response to object-directed actions. Thus, establishment of a communicative context through ostensive signals remains an important component of learning and memory into adulthood, and the pSTS may play a role in facilitating this type of social learning.

  15. Crowding, grouping, and object recognition: A matter of appearance

    PubMed Central

    Herzog, Michael H.; Sayim, Bilge; Chicherov, Vitaly; Manassi, Mauro

    2015-01-01

    In crowding, the perception of a target strongly deteriorates when neighboring elements are presented. Crowding is usually assumed to have the following characteristics. (a) Crowding is determined only by nearby elements within a restricted region around the target (Bouma's law). (b) Increasing the number of flankers can only deteriorate performance. (c) Target-flanker interference is feature-specific. These characteristics are usually explained by pooling models, which are well in the spirit of classic models of object recognition. In this review, we summarize recent findings showing that crowding is not determined by the above characteristics, thus, challenging most models of crowding. We propose that the spatial configuration across the entire visual field determines crowding. Only when one understands how all elements of a visual scene group with each other, can one determine crowding strength. We put forward the hypothesis that appearance (i.e., how stimuli look) is a good predictor for crowding, because both crowding and appearance reflect the output of recurrent processing rather than interactions during the initial phase of visual processing. PMID:26024452

  16. Crowding, grouping, and object recognition: A matter of appearance.

    PubMed

    Herzog, Michael H; Sayim, Bilge; Chicherov, Vitaly; Manassi, Mauro

    2015-01-01

    In crowding, the perception of a target strongly deteriorates when neighboring elements are presented. Crowding is usually assumed to have the following characteristics. (a) Crowding is determined only by nearby elements within a restricted region around the target (Bouma's law). (b) Increasing the number of flankers can only deteriorate performance. (c) Target-flanker interference is feature-specific. These characteristics are usually explained by pooling models, which are well in the spirit of classic models of object recognition. In this review, we summarize recent findings showing that crowding is not determined by the above characteristics, thus, challenging most models of crowding. We propose that the spatial configuration across the entire visual field determines crowding. Only when one understands how all elements of a visual scene group with each other, can one determine crowding strength. We put forward the hypothesis that appearance (i.e., how stimuli look) is a good predictor for crowding, because both crowding and appearance reflect the output of recurrent processing rather than interactions during the initial phase of visual processing.

  17. Transformation-tolerant object recognition in rats revealed by visual priming.

    PubMed

    Tafazoli, Sina; Di Filippo, Alessandro; Zoccolan, Davide

    2012-01-04

    Successful use of rodents as models for studying object vision crucially depends on the ability of their visual system to construct representations of visual objects that tolerate (i.e., remain relatively unchanged with respect to) the tremendous changes in object appearance produced, for instance, by size and viewpoint variation. Whether this is the case is still controversial, despite some recent demonstration of transformation-tolerant object recognition in rats. In fact, it remains unknown to what extent such a tolerant recognition has a spontaneous, perceptual basis, or, alternatively, mainly reflects learning of arbitrary associative relations among trained object appearances. In this study, we addressed this question by training rats to categorize a continuum of morph objects resulting from blending two object prototypes. The resulting psychometric curve (reporting the proportion of responses to one prototype along the morph line) served as a reference when, in a second phase of the experiment, either prototype was briefly presented as a prime, immediately before a test morph object. The resulting shift of the psychometric curve showed that recognition became biased toward the identity of the prime. Critically, this bias was observed also when the primes were transformed along a variety of dimensions (i.e., size, position, viewpoint, and their combination) that the animals had never experienced before. These results indicate that rats spontaneously perceive different views/appearances of an object as similar (i.e., as instances of the same object) and argue for the existence of neuronal substrates underlying formation of transformation-tolerant object representations in rats.

  18. 3D video analysis of the novel object recognition test in rats.

    PubMed

    Matsumoto, Jumpei; Uehara, Takashi; Urakawa, Susumu; Takamura, Yusaku; Sumiyoshi, Tomiki; Suzuki, Michio; Ono, Taketoshi; Nishijo, Hisao

    2014-10-01

    The novel object recognition (NOR) test has been widely used to test memory function. We developed a 3D computerized video analysis system that estimates nose contact with an object in Long Evans rats to analyze object exploration during NOR tests. The results indicate that the 3D system reproducibly and accurately scores the NOR test. Furthermore, the 3D system captures a 3D trajectory of the nose during object exploration, enabling detailed analyses of spatiotemporal patterns of object exploration. The 3D trajectory analysis revealed a specific pattern of object exploration in the sample phase of the NOR test: normal rats first explored the lower parts of objects and then gradually explored the upper parts. A systematic injection of MK-801 suppressed changes in these exploration patterns. The results, along with those of previous studies, suggest that the changes in the exploration patterns reflect neophobia to a novel object and/or changes from spatial learning to object learning. These results demonstrate that the 3D tracking system is useful not only for detailed scoring of animal behaviors but also for investigation of characteristic spatiotemporal patterns of object exploration. The system has the potential to facilitate future investigation of neural mechanisms underlying object exploration that result from dynamic and complex brain activity.

  19. The Role of Fixation and Visual Attention in Object Recognition.

    DTIC Science & Technology

    1995-01-01

    stereo by matching features and using trigonometry to convert disparity into depth lies in the matching process (correspondence problem). This is...avoid obstacles and perform other tasks which require recognizing specific objects in the environment. An active-attentive vision system is more robust

  20. Object recognition through turbulence with a modified plenoptic camera

    NASA Astrophysics Data System (ADS)

    Wu, Chensheng; Ko, Jonathan; Davis, Christopher

    2015-03-01

    Atmospheric turbulence adds accumulated distortion to images obtained by cameras and surveillance systems. When the turbulence grows stronger or when the object is further away from the observer, increasing the recording device resolution helps little to improve the quality of the image. Many sophisticated methods to correct the distorted images have been invented, such as using a known feature on or near the target object to perform a deconvolution process, or use of adaptive optics. However, most of the methods depend heavily on the object's location, and optical ray propagation through the turbulence is not directly considered. Alternatively, selecting a lucky image over many frames provides a feasible solution, but at the cost of time. In our work, we propose an innovative approach to improving image quality through turbulence by making use of a modified plenoptic camera. This type of camera adds a micro-lens array to a traditional high-resolution camera to form a semi-camera array that records duplicate copies of the object as well as "superimposed" turbulence at slightly different angles. By performing several steps of image reconstruction, turbulence effects will be suppressed to reveal more details of the object independently (without finding references near the object). Meanwhile, the redundant information obtained by the plenoptic camera raises the possibility of performing lucky image algorithmic analysis with fewer frames, which is more efficient. In our work, the details of our modified plenoptic cameras and image processing algorithms will be introduced. The proposed method can be applied to coherently illuminated object as well as incoherently illuminated objects. Our result shows that the turbulence effect can be effectively suppressed by the plenoptic camera in the hardware layer and a reconstructed "lucky image" can help the viewer identify the object even when a "lucky image" by ordinary cameras is not achievable.

  1. Acute restraint stress and corticosterone transiently disrupts novelty preference in an object recognition task.

    PubMed

    Vargas-López, Viviana; Torres-Berrio, Angélica; González-Martínez, Lina; Múnera, Alejandro; Lamprea, Marisol R

    2015-09-15

    The object recognition task is a procedure based on rodents' natural tendency to explore novel objects which is frequently used for memory testing. However, in some instances novelty preference is replaced by familiarity preference, raising questions regarding the validity of novelty preference as a pure recognition memory index. Acute stress- and corticosterone administration-induced novel object preference disruption has been frequently interpreted as memory impairment; however, it is still not clear whether such effect can be actually attributed to either mnemonic disruption or altered novelty seeking. Seventy-five adult male Wistar rats were trained in an object recognition task and subjected to either acute stress or corticosterone administration to evaluate the effect of stress or corticosterone on an object recognition task. Acute stress was induced by restraining movement for 1 or 4h, ending 30 min before the sample trial. Corticosterone was injected intraperitoneally 10 min before the test trial which was performed either 1 or 24h after the sample trial. Four-hour, but not 1-h, stress induced familiar object preference during the test trial performed 1h after the sample trial; however, acute stress had no effects on the test when performed 24h after sample trial. Systemic administration of corticosterone before the test trial performed either 1 or 24h after the sample trial also resulted in familiar object preference. However, neither acute stress nor corticosterone induced changes in locomotor behaviour. Taken together, such results suggested that acute stress probably does not induce memory retrieval impairment but, instead, induces an emotional arousing state which motivates novelty avoidance.

  2. The object pattern separation (OPS) task: a behavioral paradigm derived from the object recognition task.

    PubMed

    van Hagen, B T J; van Goethem, N P; Lagatta, D C; Prickaerts, J

    2015-05-15

    The object recognition task (ORT) is widely used to measure object memory processes in rodents. Recently, the memory process known as pattern separation has received increasing attention, as impaired pattern separation can be one of the cognitive symptoms of multiple neurological and psychiatric disorders. Pattern separation is the formation of distinct representations out of similar inputs. In the search for an easily implemented task for rodents that can be used to measure pattern separation, we developed a task derived from the ORT and the object location task (OLT), which we called the object pattern separation (OPS) task. This task aims to measure spatial pattern separation per se, which utilizes memory processes centered in the DG and CA3 region of the hippocampus. Adult male C57BL/6 mice and adult male Wistar rats were used to validate different object locations which can be used to measure spatial pattern separation. Furthermore, different inter-trial time intervals were tested with the most optimal object location, to further evaluate pattern separation-related memory in mice. We found that specific object locations show gradual effects, which is indicative of pattern separation, and that the OPS task allows the detection of spatial pattern separation bi-directionally at intermediate spatial separations. Thus, object locations and time intervals can be specifically adjusted as needed, in order to investigate an expected improvement or impairment. We conclude that the current spatial OPS task can be best described as a specific version of the ORT, which can be used to investigate pattern separation processes. Copyright © 2014 Elsevier B.V. All rights reserved.

  3. Privacy protection schemes for fingerprint recognition systems

    NASA Astrophysics Data System (ADS)

    Marasco, Emanuela; Cukic, Bojan

    2015-05-01

    The deployment of fingerprint recognition systems has always raised concerns related to personal privacy. A fingerprint is permanently associated with an individual and, generally, it cannot be reset if compromised in one application. Given that fingerprints are not a secret, potential misuses besides personal recognition represent privacy threats and may lead to public distrust. Privacy mechanisms control access to personal information and limit the likelihood of intrusions. In this paper, image- and feature-level schemes for privacy protection in fingerprint recognition systems are reviewed. Storing only key features of a biometric signature can reduce the likelihood of biometric data being used for unintended purposes. In biometric cryptosystems and biometric-based key release, the biometric component verifies the identity of the user, while the cryptographic key protects the communication channel. Transformation-based approaches only a transformed version of the original biometric signature is stored. Different applications can use different transforms. Matching is performed in the transformed domain which enable the preservation of low error rates. Since such templates do not reveal information about individuals, they are referred to as cancelable templates. A compromised template can be re-issued using a different transform. At image-level, de-identification schemes can remove identifiers disclosed for objectives unrelated to the original purpose, while permitting other authorized uses of personal information. Fingerprint images can be de-identified by, for example, mixing fingerprints or removing gender signature. In both cases, degradation of matching performance is minimized.

  4. A Scientific Workflow Platform for Generic and Scalable Object Recognition on Medical Images

    NASA Astrophysics Data System (ADS)

    Möller, Manuel; Tuot, Christopher; Sintek, Michael

    In the research project THESEUS MEDICO we aim at a system combining medical image information with semantic background knowledge from ontologies to give clinicians fully cross-modal access to biomedical image repositories. Therefore joint efforts have to be made in more than one dimension: Object detection processes have to be specified in which an abstraction is performed starting from low-level image features across landmark detection utilizing abstract domain knowledge up to high-level object recognition. We propose a system based on a client-server extension of the scientific workflow platform Kepler that assists the collaboration of medical experts and computer scientists during development and parameter learning.

  5. Regulation of object recognition and object placement by ovarian sex steroid hormones.

    PubMed

    Tuscher, Jennifer J; Fortress, Ashley M; Kim, Jaekyoon; Frick, Karyn M

    2015-05-15

    The ovarian hormones 17β-estradiol (E2) and progesterone (P4) are potent modulators of hippocampal memory formation. Both hormones have been demonstrated to enhance hippocampal memory by regulating the cellular and molecular mechanisms thought to underlie memory formation. Behavioral neuroendocrinologists have increasingly used the object recognition and object placement (object location) tasks to investigate the role of E2 and P4 in regulating hippocampal memory formation in rodents. These one-trial learning tasks are ideal for studying acute effects of hormone treatments on different phases of memory because they can be administered during acquisition (pre-training), consolidation (post-training), or retrieval (pre-testing). This review synthesizes the rodent literature testing the effects of E2 and P4 on object recognition (OR) and object placement (OP), and the molecular mechanisms in the hippocampus supporting memory formation in these tasks. Some general trends emerge from the data. Among gonadally intact females, object memory tends to be best when E2 and P4 levels are elevated during the estrous cycle, pregnancy, and in middle age. In ovariectomized females, E2 given before or immediately after testing generally enhances OR and OP in young and middle-aged rats and mice, although effects are mixed in aged rodents. Effects of E2 treatment on OR and OP memory consolidation can be mediated by both classical estrogen receptors (ERα and ERβ), and depend on glutamate receptors (NMDA, mGluR1) and activation of numerous cell signaling cascades (e.g., ERK, PI3K/Akt, mTOR) and epigenetic processes (e.g., histone acetylation, DNA methylation). Acute P4 treatment given immediately after training also enhances OR and OP in young and middle-aged ovariectomized females by activating similar cell signaling pathways as E2 (e.g., ERK, mTOR). The few studies that have administered both hormones in combination suggest that treatment can enhance OR and OP, but that effects

  6. Regulation of object recognition and object placement by ovarian sex steroid hormones

    PubMed Central

    Tuscher, Jennifer J.; Fortress, Ashley M.; Kim, Jaekyoon; Frick, Karyn M.

    2014-01-01

    The ovarian hormones 17β-estradiol (E2) and progesterone (P4) are potent modulators of hippocampal memory formation. Both hormones have been demonstrated to enhance hippocampal memory by regulating the cellular and molecular mechanisms thought to underlie memory formation. Behavioral neuroendocrinologists have increasingly used the object recognition and object placement (object location) tasks to investigate the role of E2 and P4 in regulating hippocampal memory formation in rodents. These one-trial learning tasks are ideal for studying acute effects of hormone treatments on different phases of memory because they can be administered during acquisition (pre-training), consolidation (post-training), or retrieval (pre-testing). This review synthesizes the rodent literature testing the effects of E2 and P4 on object recognition (OR) and object placement (OP), and the molecular mechanisms in the hippocampus supporting memory formation in these tasks. Some general trends emerge from the data. Among gonadally intact females, object memory tends to be best when E2 and P4 levels are elevated during the estrous cycle, pregnancy, and in middle age. In ovariectomized females, E2 given before or immediately after testing generally enhances OR and OP in young and middle-aged rats and mice, although effects are mixed in aged rodents. Effects of E2 treatment on OR 7and OP memory consolidation can be mediated by both classical estrogen receptors (ERα and ERβ), and depend on glutamate receptors (NMDA, mGluR1) and activation of numerous cell signaling cascades (e.g., ERK, PI3K/Akt, mTOR) and epigenetic processes (e.g., histone H3 acetylation, DNA methylation). Acute P4 treatment given immediately after training also enhances OR and OP in young and middle-aged ovariectomized females by activating similar cell signaling pathways as E2 (e.g., ERK, mTOR). The few studies that have administered both hormones in combination suggest that treatment can enhance OR and OP, but that

  7. Histogram of Gabor phase patterns (HGPP): a novel object representation approach for face recognition.

    PubMed

    Zhang, Baochang; Shan, Shiguang; Chen, Xilin; Gao, Wen

    2007-01-01

    A novel object descriptor, histogram of Gabor phase pattern (HGPP), is proposed for robust face recognition. In HGPP, the quadrant-bit codes are first extracted from faces based on the Gabor transformation. Global Gabor phase pattern (GGPP) and local Gabor phase pattern (LGPP) are then proposed to encode the phase variations. GGPP captures the variations derived from the orientation changing of Gabor wavelet at a given scale (frequency), while LGPP encodes the local neighborhood variations by using a novel local XOR pattern (LXP) operator. They are both divided into the nonoverlapping rectangular regions, from which spatial histograms are extracted and concatenated into an extended histogram feature to represent the original image. Finally, the recognition is performed by using the nearest-neighbor classifier with histogram intersection as the similarity measurement. The features of HGPP lie in two aspects: 1) HGPP can describe the general face images robustly without the training procedure; 2) HGPP encodes the Gabor phase information, while most previous face recognition methods exploit the Gabor magnitude information. In addition, Fisher separation criterion is further used to improve the performance of HGPP by weighing the subregions of the image according to their discriminative powers. The proposed methods are successfully applied to face recognition, and the experiment results on the large-scale FERET and CAS-PEAL databases show that the proposed algorithms significantly outperform other well-known systems in terms of recognition rate.

  8. Similarity dependency of the change in ERP component N1 accompanying with the object recognition learning.

    PubMed

    Tokudome, Wataru; Wang, Gang

    2012-01-01

    Performance during object recognition across views is largely dependent on inter-object similarity. The present study was designed to investigate the similarity dependency of object recognition learning on the changes in ERP component N1. Human subjects were asked to train themselves to recognize novel objects with different inter-object similarity by performing object recognition tasks. During the tasks, images of an object had to be discriminated from the images of other objects irrespective of the viewpoint. When objects had a high inter-object similarity, the ERP component, N1 exhibited a significant increase in both the amplitude and the latency variation across objects during the object recognition learning process, and the N1 amplitude and latency variation across the views of the same objects decreased significantly. In contrast, no significant changes were found during the learning process when using objects with low inter-object similarity. The present findings demonstrate that the changes in the variation of N1 that accompany the object recognition learning process are dependent upon the inter-object similarity and imply that there is a difference in the neuronal representation for object recognition when using objects with high and low inter-object similarity.

  9. Effect of a Bluetooth-implemented hearing aid on speech recognition performance: subjective and objective measurement.

    PubMed

    Kim, Min-Beom; Chung, Won-Ho; Choi, Jeesun; Hong, Sung Hwa; Cho, Yang-Sun; Park, Gyuseok; Lee, Sangmin

    2014-06-01

    The object was to evaluate speech perception improvement through Bluetooth-implemented hearing aids in hearing-impaired adults. Thirty subjects with bilateral symmetric moderate sensorineural hearing loss participated in this study. A Bluetooth-implemented hearing aid was fitted unilaterally in all study subjects. Objective speech recognition score and subjective satisfaction were measured with a Bluetooth-implemented hearing aid to replace the acoustic connection from either a cellular phone or a loudspeaker system. In each system, participants were assigned to 4 conditions: wireless speech signal transmission into hearing aid (wireless mode) in quiet or noisy environment and conventional speech signal transmission using external microphone of hearing aid (conventional mode) in quiet or noisy environment. Also, participants completed questionnaires to investigate subjective satisfaction. Both cellular phone and loudspeaker system situation, participants showed improvements in sentence and word recognition scores with wireless mode compared to conventional mode in both quiet and noise conditions (P < .001). Participants also reported subjective improvements, including better sound quality, less noise interference, and better accuracy naturalness, when using the wireless mode (P < .001). Bluetooth-implemented hearing aids helped to improve subjective and objective speech recognition performances in quiet and noisy environments during the use of electronic audio devices.

  10. The importance of visual features in generic vs. specialized object recognition: a computational study

    PubMed Central

    Ghodrati, Masoud; Rajaei, Karim; Ebrahimpour, Reza

    2014-01-01

    It is debated whether the representation of objects in inferior temporal (IT) cortex is distributed over activities of many neurons or there are restricted islands of neurons responsive to a specific set of objects. There are lines of evidence demonstrating that fusiform face area (FFA-in human) processes information related to specialized object recognition (here we say within category object recognition such as face identification). Physiological studies have also discovered several patches in monkey ventral temporal lobe that are responsible for facial processing. Neuronal recording from these patches shows that neurons are highly selective for face images whereas for other objects we do not see such selectivity in IT. However, it is also well-supported that objects are encoded through distributed patterns of neural activities that are distinctive for each object category. It seems that visual cortex utilize different mechanisms for between category object recognition (e.g., face vs. non-face objects) vs. within category object recognition (e.g., two different faces). In this study, we address this question with computational simulations. We use two biologically inspired object recognition models and define two experiments which address these issues. The models have a hierarchical structure of several processing layers that simply simulate visual processing from V1 to aIT. We show, through computational modeling, that the difference between these two mechanisms of recognition can underlie the visual feature and extraction mechanism. It is argued that in order to perform generic and specialized object recognition, visual cortex must separate the mechanisms involved in within category from between categories object recognition. High recognition performance in within category object recognition can be guaranteed when class-specific features with intermediate size and complexity are extracted. However, generic object recognition requires a distributed universal

  11. The importance of visual features in generic vs. specialized object recognition: a computational study.

    PubMed

    Ghodrati, Masoud; Rajaei, Karim; Ebrahimpour, Reza

    2014-01-01

    It is debated whether the representation of objects in inferior temporal (IT) cortex is distributed over activities of many neurons or there are restricted islands of neurons responsive to a specific set of objects. There are lines of evidence demonstrating that fusiform face area (FFA-in human) processes information related to specialized object recognition (here we say within category object recognition such as face identification). Physiological studies have also discovered several patches in monkey ventral temporal lobe that are responsible for facial processing. Neuronal recording from these patches shows that neurons are highly selective for face images whereas for other objects we do not see such selectivity in IT. However, it is also well-supported that objects are encoded through distributed patterns of neural activities that are distinctive for each object category. It seems that visual cortex utilize different mechanisms for between category object recognition (e.g., face vs. non-face objects) vs. within category object recognition (e.g., two different faces). In this study, we address this question with computational simulations. We use two biologically inspired object recognition models and define two experiments which address these issues. The models have a hierarchical structure of several processing layers that simply simulate visual processing from V1 to aIT. We show, through computational modeling, that the difference between these two mechanisms of recognition can underlie the visual feature and extraction mechanism. It is argued that in order to perform generic and specialized object recognition, visual cortex must separate the mechanisms involved in within category from between categories object recognition. High recognition performance in within category object recognition can be guaranteed when class-specific features with intermediate size and complexity are extracted. However, generic object recognition requires a distributed universal

  12. Deep neural networks rival the representation of primate IT cortex for core visual object recognition.

    PubMed

    Cadieu, Charles F; Hong, Ha; Yamins, Daniel L K; Pinto, Nicolas; Ardila, Diego; Solomon, Ethan A; Majaj, Najib J; DiCarlo, James J

    2014-12-01

    The primate visual system achieves remarkable visual object recognition performance even in brief presentations, and under changes to object exemplar, geometric transformations, and background variation (a.k.a. core visual object recognition). This remarkable performance is mediated by the representation formed in inferior temporal (IT) cortex. In parallel, recent advances in machine learning have led to ever higher performing models of object recognition using artificial deep neural networks (DNNs). It remains unclear, however, whether the representational performance of DNNs rivals that of the brain. To accurately produce such a comparison, a major difficulty has been a unifying metric that accounts for experimental limitations, such as the amount of noise, the number of neural recording sites, and the number of trials, and computational limitations, such as the complexity of the decoding classifier and the number of classifier training examples. In this work, we perform a direct comparison that corrects for these experimental limitations and computational considerations. As part of our methodology, we propose an extension of "kernel analysis" that measures the generalization accuracy as a function of representational complexity. Our evaluations show that, unlike previous bio-inspired models, the latest DNNs rival the representational performance of IT cortex on this visual object recognition task. Furthermore, we show that models that perform well on measures of representational performance also perform well on measures of representational similarity to IT, and on measures of predicting individual IT multi-unit responses. Whether these DNNs rely on computational mechanisms similar to the primate visual system is yet to be determined, but, unlike all previous bio-inspired models, that possibility cannot be ruled out merely on representational performance grounds.

  13. Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition

    PubMed Central

    Cadieu, Charles F.; Hong, Ha; Yamins, Daniel L. K.; Pinto, Nicolas; Ardila, Diego; Solomon, Ethan A.; Majaj, Najib J.; DiCarlo, James J.

    2014-01-01

    The primate visual system achieves remarkable visual object recognition performance even in brief presentations, and under changes to object exemplar, geometric transformations, and background variation (a.k.a. core visual object recognition). This remarkable performance is mediated by the representation formed in inferior temporal (IT) cortex. In parallel, recent advances in machine learning have led to ever higher performing models of object recognition using artificial deep neural networks (DNNs). It remains unclear, however, whether the representational performance of DNNs rivals that of the brain. To accurately produce such a comparison, a major difficulty has been a unifying metric that accounts for experimental limitations, such as the amount of noise, the number of neural recording sites, and the number of trials, and computational limitations, such as the complexity of the decoding classifier and the number of classifier training examples. In this work, we perform a direct comparison that corrects for these experimental limitations and computational considerations. As part of our methodology, we propose an extension of “kernel analysis” that measures the generalization accuracy as a function of representational complexity. Our evaluations show that, unlike previous bio-inspired models, the latest DNNs rival the representational performance of IT cortex on this visual object recognition task. Furthermore, we show that models that perform well on measures of representational performance also perform well on measures of representational similarity to IT, and on measures of predicting individual IT multi-unit responses. Whether these DNNs rely on computational mechanisms similar to the primate visual system is yet to be determined, but, unlike all previous bio-inspired models, that possibility cannot be ruled out merely on representational performance grounds. PMID:25521294

  14. Cognitive impairment in old rats: a comparison of object displacement, object recognition and water maze.

    PubMed

    Luparini, M R; Del Vecchio, A; Barillari, G; Magnani, M; Prosdocimi, M

    2000-08-01

    The behavioral performance of young and aged rats was studied in a repeated-trials test. Young animals reacted to both spatial displacement and novelty, whereas most aged rats lost the ability to react to novelty although maintaining spatial memory. The cluster analysis procedure performed on all the tested subjects enabled the recognition of a consistent group of the aged sample (35%) with a mild degree of spatial and non-spatial memory impairment. Spatial memory impairment of some of the aged animals was also evaluated in the Morris water maze test. On the fifth day of the task, we observed a very low percentage of impaired aged animals, which partially corresponded to the impaired group identified by the object recognition test. In contrast, the subgroup of mildly impaired rats performed similarly to the young animals. We advance that the Morris water maze might represent a stressful experimental condition for aged rats, enhancing the motivational level of animals subjected to this procedure. This condition may alter the cognitive responses. As a consequence, the "mildly impaired" rats, which may be considered an interesting group for investigating memory-enhancing drugs, will infrequently be recognized with the Morris water maze test. Cognitive impairment in aged rats should be studied utilizing a sensitive test in which motivation does not substantially influence the results of the test.

  15. Role of the dentate gyrus in mediating object-spatial configuration recognition.

    PubMed

    Kesner, Raymond P; Taylor, James O; Hoge, Jennifer; Andy, Ford

    2015-02-01

    In the present study the effects of dorsal dentate gyrus (dDG) lesions in rats were tested on recognition memory tasks based on the interaction between objects, features of objects, and spatial features. The results indicated that the rats with dDG lesions did not differ from controls in recognition for a change within object feature configuration and object recognition tasks. In contrast, there was a deficit for the dDG lesioned rats relative to controls in recognition for a change within object-spatial feature configuration, complex object-place feature configuration and spatial recognition tasks. It is suggested that the dDG subregion of the hippocampus supports object-place and complex object-place feature information via a conjunctive encoding process.

  16. Sensor-independent approach to recognition: the object-based approach

    NASA Astrophysics Data System (ADS)

    Morrow, Jim C.; Hossain, Sqama

    1994-03-01

    This paper introduces a fundamentally different approach to recognition -- the object-based approach -- which is inherently knowledge-based and sensor independent. The paper begins with a description of an object-based recognition system, contrasting it with the image-based approach. Next, the multilevel stage of the system, incorporating several sensor data sources is described. From these sources elements of the situation hypothesis are generated as directed by the recognition goal. Depending on the degree of correspondence between the sensor-fed elements and the object-model-fed elements, a hypothetical element is created. The hypothetical element is further employed to develop evidence for the sensor-fed element through the inclusion of secondary sensor outputs. The sensor-fed element is thus modeled in more detail, and further evidence is added to the hypothetical element. Several levels of reasoning and data integration are involved in this overall process; further, a self-adjusting correction mechanism is included through the feedback from the hypothetical element to the sensors, thus defining secondary output connections to the sensor-fed element. Some preliminary work based on this approach has been carried out and initial results show improvements over the conventional image-based approach.

  17. Research on recognition methods of aphid objects in complex backgrounds

    NASA Astrophysics Data System (ADS)

    Zhao, Hui-Yan; Zhang, Ji-Hong

    2009-07-01

    In order to improve the recognition accuracy among the kinds of aphids in the complex backgrounds, the recognition method among kinds of aphids based on Dual-Tree Complex Wavelet Transform (DT-CWT) and Support Vector Machine (Libsvm) is proposed. Firstly the image is pretreated; secondly the aphid images' texture feature of three crops are extracted by DT-CWT in order to get the training parameters of training model; finally the training model could recognize aphids among the three kinds of crops. By contrasting to Gabor wavelet transform and the traditional extracting texture's methods based on Gray-Level Co-Occurrence Matrix (GLCM), the experiment result shows that the method has a certain practicality and feasibility and provides basic for aphids' recognition between the identification among same kind aphid.

  18. Crossmodal enhancement in the LOC for visuohaptic object recognition over development.

    PubMed

    Jao, R Joanne; James, Thomas W; James, Karin Harman

    2015-10-01

    Research has provided strong evidence of multisensory convergence of visual and haptic information within the visual cortex. These studies implement crossmodal matching paradigms to examine how systems use information from different sensory modalities for object recognition. Developmentally, behavioral evidence of visuohaptic crossmodal processing has suggested that communication within sensory systems develops earlier than across systems; nonetheless, it is unknown how the neural mechanisms driving these behavioral effects develop. To address this gap in knowledge, BOLD functional Magnetic Resonance Imaging (fMRI) was measured during delayed match-to-sample tasks that examined intramodal (visual-to-visual, haptic-to-haptic) and crossmodal (visual-to-haptic, haptic-to-visual) novel object recognition in children aged 7-8.5 years and adults. Tasks were further divided into sample encoding and test matching phases to dissociate the relative contributions of each. Results of crossmodal and intramodal object recognition revealed the network of known visuohaptic multisensory substrates, including the lateral occipital complex (LOC) and the intraparietal sulcus (IPS). Critically, both adults and children showed crossmodal enhancement within the LOC, suggesting a sensitivity to changes in sensory modality during recognition. These groups showed similar regions of activation, although children generally exhibited more widespread activity during sample encoding and weaker BOLD signal change during test matching than adults. Results further provided evidence of a bilateral region in the occipitotemporal cortex that was haptic-preferring in both age groups. This region abutted the bimodal LOtv, and was consistent with a medial to lateral organization that transitioned from a visual to haptic bias within the LOC. These findings converge with existing evidence of visuohaptic processing in the LOC in adults, and extend our knowledge of crossmodal processing in adults and

  19. Crossmodal enhancement in the LOC for visuohaptic object recognition over development

    PubMed Central

    Jao, R. Joanne; James, Thomas W.; James, Karin Harman

    2015-01-01

    Research has provided strong evidence of multisensory convergence of visual and haptic information within the visual cortex. These studies implement crossmodal matching paradigms to examine how systems use information from different sensory modalities for object recognition. Developmentally, behavioral evidence of visuohaptic crossmodal processing has suggested that communication within sensory systems develops earlier than across systems; nonetheless, it is unknown how the neural mechanisms driving these behavioral effects develop. To address this gap in knowledge, BOLD functional Magnetic Resonance Imaging (fMRI) was measured during delayed match-to-sample tasks that examined intramodal (visual-to-visual, haptic-to-haptic) and crossmodal (visual-to-haptic, haptic-to-visual) novel object recognition in children aged 7 to 8.5 years and adults. Tasks were further divided into sample encoding and test matching phases to dissociate the relative contributions of each. Results of crossmodal and intramodal object recognition revealed the network of known visuohaptic multisensory substrates, including the lateral occipital complex (LOC) and the intraparietal sulcus (IPS). Critically, both adults and children showed crossmodal enhancement within the LOC, suggesting a sensitivity to changes in sensory modality during recognition. These groups showed similar regions of activation, although children generally exhibited more widespread activity during sample encoding and weaker BOLD signal change during test matching than adults. Results further provided evidence of a bilateral region in the occipitotemporal cortex that was haptic-preferring in both age groups. This region abutted the bimodal LOtv, and was consistent with a medial to lateral organization that transitioned from a visual to haptic bias within the LOC. These findings converge with existing evidence of visuohaptic processing in the LOC in adults, and extend our knowledge of crossmodal processing in adults and

  20. Crossmodal object recognition in rats with and without multimodal object pre-exposure: no effect of hippocampal lesions.

    PubMed

    Reid, James M; Jacklin, Derek L; Winters, Boyer D

    2012-10-01

    The neural mechanisms and brain circuitry involved in the formation, storage, and utilization of multisensory object representations are poorly understood. We have recently introduced a crossmodal object recognition (CMOR) task that enables the study of such questions in rats. Our previous research has indicated that the perirhinal and posterior parietal cortices functionally interact to mediate spontaneous (tactile-to-visual) CMOR performance in rats; however, it remains to be seen whether other brain regions, particularly those receiving polymodal sensory inputs, contribute to this cognitive function. In the current study, we assessed the potential contribution of one such polymodal region, the hippocampus (HPC), to crossmodal object recognition memory. Rats with bilateral excitotoxic HPC lesions were tested in two versions of crossmodal object recognition: (1) the original CMOR task, which requires rats to compare between a stored tactile object representation and visually-presented objects to discriminate the novel and familiar stimuli; and (2) a novel 'multimodal pre-exposure' version of the CMOR task (PE/CMOR), in which simultaneous exploration of the tactile and visual sensory features of an object 24 h prior to the sample phase enhances CMOR performance across longer retention delays. Hippocampus-lesioned rats performed normally on both crossmodal object recognition tasks, but were impaired on a radial arm maze test of spatial memory, demonstrating the functional effectiveness of the lesions. These results strongly suggest that the HPC, despite its polymodal anatomical connections, is not critically involved in tactile-to-visual crossmodal object recognition memory.

  1. Kannada character recognition system using neural network

    NASA Astrophysics Data System (ADS)

    Kumar, Suresh D. S.; Kamalapuram, Srinivasa K.; Kumar, Ajay B. R.

    2013-03-01

    Handwriting recognition has been one of the active and challenging research areas in the field of pattern recognition. It has numerous applications which include, reading aid for blind, bank cheques and conversion of any hand written document into structural text form. As there is no sufficient number of works on Indian language character recognition especially Kannada script among 15 major scripts in India. In this paper an attempt is made to recognize handwritten Kannada characters using Feed Forward neural networks. A handwritten Kannada character is resized into 20x30 Pixel. The resized character is used for training the neural network. Once the training process is completed the same character is given as input to the neural network with different set of neurons in hidden layer and their recognition accuracy rate for different Kannada characters has been calculated and compared. The results show that the proposed system yields good recognition accuracy rates comparable to that of other handwritten character recognition systems.

  2. Experience moderates overlap between object and face recognition, suggesting a common ability

    PubMed Central

    Gauthier, Isabel; McGugin, Rankin W.; Richler, Jennifer J.; Herzmann, Grit; Speegle, Magen; Van Gulick, Ana E.

    2014-01-01

    Some research finds that face recognition is largely independent from the recognition of other objects; a specialized and innate ability to recognize faces could therefore have little or nothing to do with our ability to recognize objects. We propose a new framework in which recognition performance for any category is the product of domain-general ability and category-specific experience. In Experiment 1, we show that the overlap between face and object recognition depends on experience with objects. In 256 subjects we measured face recognition, object recognition for eight categories, and self-reported experience with these categories. Experience predicted neither face recognition nor object recognition but moderated their relationship: Face recognition performance is increasingly similar to object recognition performance with increasing object experience. If a subject has a lot of experience with objects and is found to perform poorly, they also prove to have a low ability with faces. In a follow-up survey, we explored the dimensions of experience with objects that may have contributed to self-reported experience in Experiment 1. Different dimensions of experience appear to be more salient for different categories, with general self-reports of expertise reflecting judgments of verbal knowledge about a category more than judgments of visual performance. The complexity of experience and current limitations in its measurement support the importance of aggregating across multiple categories. Our findings imply that both face and object recognition are supported by a common, domain-general ability expressed through experience with a category and best measured when accounting for experience. PMID:24993021

  3. Experience moderates overlap between object and face recognition, suggesting a common ability.

    PubMed

    Gauthier, Isabel; McGugin, Rankin W; Richler, Jennifer J; Herzmann, Grit; Speegle, Magen; Van Gulick, Ana E

    2014-07-03

    Some research finds that face recognition is largely independent from the recognition of other objects; a specialized and innate ability to recognize faces could therefore have little or nothing to do with our ability to recognize objects. We propose a new framework in which recognition performance for any category is the product of domain-general ability and category-specific experience. In Experiment 1, we show that the overlap between face and object recognition depends on experience with objects. In 256 subjects we measured face recognition, object recognition for eight categories, and self-reported experience with these categories. Experience predicted neither face recognition nor object recognition but moderated their relationship: Face recognition performance is increasingly similar to object recognition performance with increasing object experience. If a subject has a lot of experience with objects and is found to perform poorly, they also prove to have a low ability with faces. In a follow-up survey, we explored the dimensions of experience with objects that may have contributed to self-reported experience in Experiment 1. Different dimensions of experience appear to be more salient for different categories, with general self-reports of expertise reflecting judgments of verbal knowledge about a category more than judgments of visual performance. The complexity of experience and current limitations in its measurement support the importance of aggregating across multiple categories. Our findings imply that both face and object recognition are supported by a common, domain-general ability expressed through experience with a category and best measured when accounting for experience. © 2014 ARVO.

  4. Practical automatic Arabic license plate recognition system

    NASA Astrophysics Data System (ADS)

    Mohammad, Khader; Agaian, Sos; Saleh, Hani

    2011-02-01

    Since 1970's, the need of an automatic license plate recognition system, sometimes referred as Automatic License Plate Recognition system, has been increasing. A license plate recognition system is an automatic system that is able to recognize a license plate number, extracted from image sensors. In specific, Automatic License Plate Recognition systems are being used in conjunction with various transportation systems in application areas such as law enforcement (e.g. speed limit enforcement) and commercial usages such as parking enforcement and automatic toll payment private and public entrances, border control, theft and vandalism control. Vehicle license plate recognition has been intensively studied in many countries. Due to the different types of license plates being used, the requirement of an automatic license plate recognition system is different for each country. [License plate detection using cluster run length smoothing algorithm ].Generally, an automatic license plate localization and recognition system is made up of three modules; license plate localization, character segmentation and optical character recognition modules. This paper presents an Arabic license plate recognition system that is insensitive to character size, font, shape and orientation with extremely high accuracy rate. The proposed system is based on a combination of enhancement, license plate localization, morphological processing, and feature vector extraction using the Haar transform. The performance of the system is fast due to classification of alphabet and numerals based on the license plate organization. Experimental results for license plates of two different Arab countries show an average of 99 % successful license plate localization and recognition in a total of more than 20 different images captured from a complex outdoor environment. The results run times takes less time compared to conventional and many states of art methods.

  5. Higher-Order Neural Networks Applied to 2D and 3D Object Recognition

    NASA Technical Reports Server (NTRS)

    Spirkovska, Lilly; Reid, Max B.

    1994-01-01

    A Higher-Order Neural Network (HONN) can be designed to be invariant to geometric transformations such as scale, translation, and in-plane rotation. Invariances are built directly into the architecture of a HONN and do not need to be learned. Thus, for 2D object recognition, the network needs to be trained on just one view of each object class, not numerous scaled, translated, and rotated views. Because the 2D object recognition task is a component of the 3D object recognition task, built-in 2D invariance also decreases the size of the training set required for 3D object recognition. We present results for 2D object recognition both in simulation and within a robotic vision experiment and for 3D object recognition in simulation. We also compare our method to other approaches and show that HONNs have distinct advantages for position, scale, and rotation-invariant object recognition. The major drawback of HONNs is that the size of the input field is limited due to the memory required for the large number of interconnections in a fully connected network. We present partial connectivity strategies and a coarse-coding technique for overcoming this limitation and increasing the input field to that required by practical object recognition problems.

  6. Using an Improved SIFT Algorithm and Fuzzy Closed-Loop Control Strategy for Object Recognition in Cluttered Scenes

    PubMed Central

    Nie, Haitao; Long, Kehui; Ma, Jun; Yue, Dan; Liu, Jinguo

    2015-01-01

    Partial occlusions, large pose variations, and extreme ambient illumination conditions generally cause the performance degradation of object recognition systems. Therefore, this paper presents a novel approach for fast and robust object recognition in cluttered scenes based on an improved scale invariant feature transform (SIFT) algorithm and a fuzzy closed-loop control method. First, a fast SIFT algorithm is proposed by classifying SIFT features into several clusters based on several attributes computed from the sub-orientation histogram (SOH), in the feature matching phase only features that share nearly the same corresponding attributes are compared. Second, a feature matching step is performed following a prioritized order based on the scale factor, which is calculated between the object image and the target object image, guaranteeing robust feature matching. Finally, a fuzzy closed-loop control strategy is applied to increase the accuracy of the object recognition and is essential for autonomous object manipulation process. Compared to the original SIFT algorithm for object recognition, the result of the proposed method shows that the number of SIFT features extracted from an object has a significant increase, and the computing speed of the object recognition processes increases by more than 40%. The experimental results confirmed that the proposed method performs effectively and accurately in cluttered scenes. PMID:25714094

  7. Insular Cortex Is Involved in Consolidation of Object Recognition Memory

    ERIC Educational Resources Information Center

    Bermudez-Rattoni, Federico; Okuda, Shoki; Roozendaal, Benno; McGaugh, James L.

    2005-01-01

    Extensive evidence indicates that the insular cortex (IC), also termed gustatory cortex, is critically involved in conditioned taste aversion and taste recognition memory. Although most studies of the involvement of the IC in memory have investigated taste, there is some evidence that the IC is involved in memory that is not based on taste. In…

  8. Performance Evaluation of Neuromorphic-Vision Object Recognition Algorithms

    DTIC Science & Technology

    2014-08-01

    Malibu Canyon Rd, Malibu, CA 90265, USA Lior Elazary, Randolph C. Voorhies, Daniel F. Parks, Laurent Itti University of Southern California 3641...and Pattern Recognition, CVPR’07, pp. 1-8. [12] Carpenter , G., Grossberg, S. and Reynolds. J.H. (1991), “ARTMAP: Supervised real-time learning and

  9. Graph - Based High Resolution Satellite Image Segmentation for Object Recognition

    NASA Astrophysics Data System (ADS)

    Ravali, K.; Kumar, M. V. Ravi; Venugopala Rao, K.

    2014-11-01

    Object based image processing and analysis is challenging research in very high resolution satellite utilisation. Commonly ei ther pixel based classification or visual interpretation is used to recognize and delineate land cover categories. The pixel based classification techniques use rich spectral content of satellite images and fail to utilise spatial relations. To overcome th is drawback, traditional time consuming visual interpretation methods are being used operational ly for preparation of thematic maps. This paper addresses computational vision principles to object level image segmentation. In this study, computer vision algorithms are developed to define the boundary between two object regions and segmentation by representing image as graph. Image is represented as a graph G (V, E), where nodes belong to pixels and, edges (E) connect nodes belonging to neighbouring pixels. The transformed Mahalanobis distance has been used to define a weight function for partition of graph into components such that each component represents the region of land category. This implies that edges between two vertices in the same component have relatively low weights and edges between vertices in different components should have higher weights. The derived segments are categorised to different land cover using supervised classification. The paper presents the experimental results on real world multi-spectral remote sensing images of different landscapes such as Urban, agriculture and mixed land cover. Graph construction done in C program and list the run time for both graph construction and segmentation calculation on dual core Intel i7 system with 16 GB RAM, running 64bit window 7.

  10. Multifeatural shape processing in rats engaged in invariant visual object recognition.

    PubMed

    Alemi-Neissi, Alireza; Rosselli, Federica Bianca; Zoccolan, Davide

    2013-04-03

    The ability to recognize objects despite substantial variation in their appearance (e.g., because of position or size changes) represents such a formidable computational feat that it is widely assumed to be unique to primates. Such an assumption has restricted the investigation of its neuronal underpinnings to primate studies, which allow only a limited range of experimental approaches. In recent years, the increasingly powerful array of optical and molecular tools that has become available in rodents has spurred a renewed interest for rodent models of visual functions. However, evidence of primate-like visual object processing in rodents is still very limited and controversial. Here we show that rats are capable of an advanced recognition strategy, which relies on extracting the most informative object features across the variety of viewing conditions the animals may face. Rat visual strategy was uncovered by applying an image masking method that revealed the features used by the animals to discriminate two objects across a range of sizes, positions, in-depth, and in-plane rotations. Noticeably, rat recognition relied on a combination of multiple features that were mostly preserved across the transformations the objects underwent, and largely overlapped with the features that a simulated ideal observer deemed optimal to accomplish the discrimination task. These results indicate that rats are able to process and efficiently use shape information, in a way that is largely tolerant to variation in object appearance. This suggests that their visual system may serve as a powerful model to study the neuronal substrates of object recognition.

  11. A rodent model for the study of invariant visual object recognition

    PubMed Central

    Zoccolan, Davide; Oertelt, Nadja; DiCarlo, James J.; Cox, David D.

    2009-01-01

    The human visual system is able to recognize objects despite tremendous variation in their appearance on the retina resulting from variation in view, size, lighting, etc. This ability—known as “invariant” object recognition—is central to visual perception, yet its computational underpinnings are poorly understood. Traditionally, nonhuman primates have been the animal model-of-choice for investigating the neuronal substrates of invariant recognition, because their visual systems closely mirror our own. Meanwhile, simpler and more accessible animal models such as rodents have been largely overlooked as possible models of higher-level visual functions, because their brains are often assumed to lack advanced visual processing machinery. As a result, little is known about rodents' ability to process complex visual stimuli in the face of real-world image variation. In the present work, we show that rats possess more advanced visual abilities than previously appreciated. Specifically, we trained pigmented rats to perform a visual task that required them to recognize objects despite substantial variation in their appearance, due to changes in size, view, and lighting. Critically, rats were able to spontaneously generalize to previously unseen transformations of learned objects. These results provide the first systematic evidence for invariant object recognition in rats and argue for an increased focus on rodents as models for studying high-level visual processing. PMID:19429704

  12. Humans and Deep Networks Largely Agree on Which Kinds of Variation Make Object Recognition Harder

    PubMed Central

    Kheradpisheh, Saeed R.; Ghodrati, Masoud; Ganjtabesh, Mohammad; Masquelier, Timothée

    2016-01-01

    View-invariant object recognition is a challenging problem that has attracted much attention among the psychology, neuroscience, and computer vision communities. Humans are notoriously good at it, even if some variations are presumably more difficult to handle than others (e.g., 3D rotations). Humans are thought to solve the problem through hierarchical processing along the ventral stream, which progressively extracts more and more invariant visual features. This feed-forward architecture has inspired a new generation of bio-inspired computer vision systems called deep convolutional neural networks (DCNN), which are currently the best models for object recognition in natural images. Here, for the first time, we systematically compared human feed-forward vision and DCNNs at view-invariant object recognition task using the same set of images and controlling the kinds of transformation (position, scale, rotation in plane, and rotation in depth) as well as their magnitude, which we call “variation level.” We used four object categories: car, ship, motorcycle, and animal. In total, 89 human subjects participated in 10 experiments in which they had to discriminate between two or four categories after rapid presentation with backward masking. We also tested two recent DCNNs (proposed respectively by Hinton's group and Zisserman's group) on the same tasks. We found that humans and DCNNs largely agreed on the relative difficulties of each kind of variation: rotation in depth is by far the hardest transformation to handle, followed by scale, then rotation in plane, and finally position (much easier). This suggests that DCNNs would be reasonable models of human feed-forward vision. In addition, our results show that the variation levels in rotation in depth and scale strongly modulate both humans' and DCNNs' recognition performances. We thus argue that these variations should be controlled in the image datasets used in vision research. PMID:27642281

  13. Humans and Deep Networks Largely Agree on Which Kinds of Variation Make Object Recognition Harder.

    PubMed

    Kheradpisheh, Saeed R; Ghodrati, Masoud; Ganjtabesh, Mohammad; Masquelier, Timothée

    2016-01-01

    View-invariant object recognition is a challenging problem that has attracted much attention among the psychology, neuroscience, and computer vision communities. Humans are notoriously good at it, even if some variations are presumably more difficult to handle than others (e.g., 3D rotations). Humans are thought to solve the problem through hierarchical processing along the ventral stream, which progressively extracts more and more invariant visual features. This feed-forward architecture has inspired a new generation of bio-inspired computer vision systems called deep convolutional neural networks (DCNN), which are currently the best models for object recognition in natural images. Here, for the first time, we systematically compared human feed-forward vision and DCNNs at view-invariant object recognition task using the same set of images and controlling the kinds of transformation (position, scale, rotation in plane, and rotation in depth) as well as their magnitude, which we call "variation level." We used four object categories: car, ship, motorcycle, and animal. In total, 89 human subjects participated in 10 experiments in which they had to discriminate between two or four categories after rapid presentation with backward masking. We also tested two recent DCNNs (proposed respectively by Hinton's group and Zisserman's group) on the same tasks. We found that humans and DCNNs largely agreed on the relative difficulties of each kind of variation: rotation in depth is by far the hardest transformation to handle, followed by scale, then rotation in plane, and finally position (much easier). This suggests that DCNNs would be reasonable models of human feed-forward vision. In addition, our results show that the variation levels in rotation in depth and scale strongly modulate both humans' and DCNNs' recognition performances. We thus argue that these variations should be controlled in the image datasets used in vision research.

  14. The development of newborn object recognition in fast and slow visual worlds.

    PubMed

    Wood, Justin N; Wood, Samantha M W

    2016-04-27

    Object recognition is central to perception and cognition. Yet relatively little is known about the environmental factors that cause invariant object recognition to emerge in the newborn brain. Is this ability a hardwired property of vision? Or does the development of invariant object recognition require experience with a particular kind of visual environment? Here, we used a high-throughput controlled-rearing method to examine whether newborn chicks (Gallus gallus) require visual experience with slowly changing objects to develop invariant object recognition abilities. When newborn chicks were raised with a slowly rotating virtual object, the chicks built invariant object representations that generalized across novel viewpoints and rotation speeds. In contrast, when newborn chicks were raised with a virtual object that rotated more quickly, the chicks built viewpoint-specific object representations that failed to generalize to novel viewpoints and rotation speeds. Moreover, there was a direct relationship between the speed of the object and the amount of invariance in the chick's object representation. Thus, visual experience with slowly changing objects plays a critical role in the development of invariant object recognition. These results indicate that invariant object recognition is not a hardwired property of vision, but is learned rapidly when newborns encounter a slowly changing visual world.

  15. The development of newborn object recognition in fast and slow visual worlds

    PubMed Central

    Wood, Justin N.; Wood, Samantha M. W.

    2016-01-01

    Object recognition is central to perception and cognition. Yet relatively little is known about the environmental factors that cause invariant object recognition to emerge in the newborn brain. Is this ability a hardwired property of vision? Or does the development of invariant object recognition require experience with a particular kind of visual environment? Here, we used a high-throughput controlled-rearing method to examine whether newborn chicks (Gallus gallus) require visual experience with slowly changing objects to develop invariant object recognition abilities. When newborn chicks were raised with a slowly rotating virtual object, the chicks built invariant object representations that generalized across novel viewpoints and rotation speeds. In contrast, when newborn chicks were raised with a virtual object that rotated more quickly, the chicks built viewpoint-specific object representations that failed to generalize to novel viewpoints and rotation speeds. Moreover, there was a direct relationship between the speed of the object and the amount of invariance in the chick's object representation. Thus, visual experience with slowly changing objects plays a critical role in the development of invariant object recognition. These results indicate that invariant object recognition is not a hardwired property of vision, but is learned rapidly when newborns encounter a slowly changing visual world. PMID:27097925

  16. Post-Training Reversible Inactivation of the Hippocampus Enhances Novel Object Recognition Memory

    ERIC Educational Resources Information Center

    Oliveira, Ana M. M.; Hawk, Joshua D.; Abel, Ted; Havekes, Robbert

    2010-01-01

    Research on the role of the hippocampus in object recognition memory has produced conflicting results. Previous studies have used permanent hippocampal lesions to assess the requirement for the hippocampus in the object recognition task. However, permanent hippocampal lesions may impact performance through effects on processes besides memory…

  17. The Consolidation of Object and Context Recognition Memory Involve Different Regions of the Temporal Lobe

    ERIC Educational Resources Information Center

    Balderas, Israela; Rodriguez-Ortiz, Carlos J.; Salgado-Tonda, Paloma; Chavez-Hurtado, Julio; McGaugh, James L.; Bermudez-Rattoni, Federico

    2008-01-01

    These experiments investigated the involvement of several temporal lobe regions in consolidation of recognition memory. Anisomycin, a protein synthesis inhibitor, was infused into the hippocampus, perirhinal cortex, insular cortex, or basolateral amygdala of rats immediately after the sample phase of object or object-in-context recognition memory…

  18. Post-Training Reversible Inactivation of the Hippocampus Enhances Novel Object Recognition Memory

    ERIC Educational Resources Information Center

    Oliveira, Ana M. M.; Hawk, Joshua D.; Abel, Ted; Havekes, Robbert

    2010-01-01

    Research on the role of the hippocampus in object recognition memory has produced conflicting results. Previous studies have used permanent hippocampal lesions to assess the requirement for the hippocampus in the object recognition task. However, permanent hippocampal lesions may impact performance through effects on processes besides memory…

  19. The Consolidation of Object and Context Recognition Memory Involve Different Regions of the Temporal Lobe

    ERIC Educational Resources Information Center

    Balderas, Israela; Rodriguez-Ortiz, Carlos J.; Salgado-Tonda, Paloma; Chavez-Hurtado, Julio; McGaugh, James L.; Bermudez-Rattoni, Federico

    2008-01-01

    These experiments investigated the involvement of several temporal lobe regions in consolidation of recognition memory. Anisomycin, a protein synthesis inhibitor, was infused into the hippocampus, perirhinal cortex, insular cortex, or basolateral amygdala of rats immediately after the sample phase of object or object-in-context recognition memory…

  20. To what extent can matching algorithms based on direct outputs of spatial filters account for human object recognition?

    PubMed

    Fiser, J; Biederman, I; Cooper, E E

    1996-01-01

    A number of recent successful models of face recognition posit only two layers, an input layer consisting of a lattice of spatial filters and a single subsequent stage by which those descriptor values are mapped directly onto an object representation layer by standard matching methods such as stochastic optimization. Is this approach sufficient for modeling human object recognition? We tested whether a highly efficient version of such a two-layer model would manifest effects similar to those shown by humans when given the task of recognizing images of objects that had been employed in a series of psychophysical experiments. System accuracy was quite high overall, but was qualitatively different from that evidenced by humans in object recognition tasks. The discrepancy between the system's performance and human performance is likely to be revealed by all models that map filter values directly onto object units. These results suggest that human object recognition (as opposed to face recognition) may be difficult to approximate by models that do not posit hidden units for explicit representation of intermediate entities such as edges, viewpoint invariant classifiers, axes, shocks and object parts.

  1. Haptic Object Recognition is View-Independent in Early Blind but not Sighted People.

    PubMed

    Occelli, Valeria; Lacey, Simon; Stephens, Careese; John, Thomas; Sathian, K

    2016-03-01

    Object recognition, whether visual or haptic, is impaired in sighted people when objects are rotated between learning and test, relative to an unrotated condition, that is, recognition is view-dependent. Loss of vision early in life results in greater reliance on haptic perception for object identification compared with the sighted. Therefore, we hypothesized that early blind people may be more adept at recognizing objects despite spatial transformations. To test this hypothesis, we compared early blind and sighted control participants on a haptic object recognition task. Participants studied pairs of unfamiliar three-dimensional objects and performed a two-alternative forced-choice identification task, with the learned objects presented both unrotated and rotated 180° about they-axis. Rotation impaired the recognition accuracy of sighted, but not blind, participants. We propose that, consistent with our hypothesis, haptic view-independence in the early blind reflects their greater experience with haptic object perception.

  2. Haptic object recognition is view-independent in early blind but not sighted people

    PubMed Central

    Occelli, Valeria; Lacey, Simon; Stephens, Careese; John, Thomas; Sathian, K.

    2016-01-01

    Object recognition, whether visual or haptic, is impaired in sighted people when objects are rotated between learning and test, relative to an unrotated condition, i.e., recognition is view-dependent. Loss of vision early in life results in greater reliance on haptic perception for object identification compared to the sighted. Therefore, we hypothesized that early blind people may be more adept at recognizing objects despite spatial transformations. To test this hypothesis, we compared early blind and sighted control participants on a haptic object recognition task. Participants studied pairs of unfamiliar 3-D objects and performed a two-alternative forced-choice identification task, with the learned objects presented both unrotated and rotated 180° about the y-axis. Rotation impaired the recognition accuracy of sighted, but not blind, participants. We propose that, consistent with our hypothesis, haptic view-independence in the early blind reflects their greater experience with haptic object perception. PMID:26562881

  3. Toward the ultimate synthesis/recognition system.

    PubMed

    Furui, S

    1995-10-24

    This paper predicts speech synthesis, speech recognition, and speaker recognition technology for the year 2001, and it describes the most important research problems to be solved in order to arrive at these ultimate synthesis and recognition systems. The problems for speech synthesis include natural and intelligible voice production, prosody control based on meaning, capability of controlling synthesized voice quality and choosing individual speaking style, multilingual and multidialectal synthesis, choice of application-oriented speaking styles, capability of adding emotion, and synthesis from concepts. The problems for speech recognition include robust recognition against speech variations, adaptation/normalization to variations due to environmental conditions and speakers, automatic knowledge acquisition for acoustic and linguistic modeling, spontaneous speech recognition, naturalness and ease of human-machine interaction, and recognition of emotion. The problems for speaker recognition are similar to those for speech recognition. The research topics related to all these techniques include the use of articulatory and perceptual constraints and evaluation methods for measuring the quality of technology and systems.

  4. α₄β₂ Nicotinic receptor stimulation of the GABAergic system within the orbitofrontal cortex ameliorates the severe crossmodal object recognition impairment in ketamine-treated rats: implications for cognitive dysfunction in schizophrenia.

    PubMed

    Cloke, Jacob M; Winters, Boyer D

    2015-03-01

    Schizophrenia is associated with atypical multisensory integration. Rats treated sub-chronically with NMDA receptor antagonists to model schizophrenia are severely impaired on a tactile-to-visual crossmodal object recognition (CMOR) task, and this deficit is reversed by systemic nicotine. The current study assessed the receptor specificity of the ameliorative effect of nicotine in the CMOR task, as well as the potential for nicotinic receptor (nAChR) interactions with GABA and glutamate. Male Long-Evans rats were treated sub-chronically for 10 days with ketamine or saline and then tested on the CMOR task after a 10-day washout. Systemic nicotine given before the sample phase of the CMOR task reversed the ketamine-induced impairment, but this effect was blocked by co-administration of the GABAA receptor antagonist bicuculline at a dosage that itself did not cause impairment. Pre-sample systemic co-administration of the NMDA receptor antagonist MK-801 did not block the remediating effect of nicotine in ketamine-treated rats. The selective α7 nAChR agonist GTS-21 and α4β2 nAChR agonist ABT-418 were also tested, with only the latter reversing the ketamine impairment dose-dependently; bicuculline also blocked this effect. Similarly, infusions of nicotine or ABT-418 into the orbitofrontal cortex (OFC) reversed the CMOR impairment in ketamine-treated rats, and systemic bicuculline blocked the effect of intra-OFC ABT-418. These results suggest that nicotine-induced agonism of α4β2 nAChRs within the OFC ameliorates CMOR deficits in ketamine-treated rats via stimulation of the GABAergic system. The findings of this research may have important implications for understanding the nature and potential treatment of cognitive impairment in schizophrenia.

  5. BOLD activity during mental rotation and viewpoint-dependent object recognition.

    PubMed

    Gauthier, Isabel; Hayward, William G; Tarr, Michael J; Anderson, Adam W; Skudlarski, Pawel; Gore, John C

    2002-03-28

    We measured brain activity during mental rotation and object recognition with objects rotated around three different axes. Activity in the superior parietal lobe (SPL) increased proportionally to viewpoint disparity during mental rotation, but not during object recognition. In contrast, the fusiform gyrus was preferentially recruited in a viewpoint-dependent manner in recognition as compared to mental rotation. In addition, independent of the effect of viewpoint, object recognition was associated with ventral areas and mental rotation with dorsal areas. These results indicate that the similar behavioral effects of viewpoint obtained in these two tasks are based on different neural substrates. Such findings call into question the hypothesis that mental rotation is used to compensate for changes in viewpoint during object recognition.

  6. Differential effects of spaced vs. massed training in long-term object-identity and object-location recognition memory.

    PubMed

    Bello-Medina, Paola C; Sánchez-Carrasco, Livia; González-Ornelas, Nadia R; Jeffery, Kathryn J; Ramírez-Amaya, Víctor

    2013-08-01

    Here we tested whether the well-known superiority of spaced training over massed training is equally evident in both object identity and object location recognition memory. We trained animals with objects placed in a variable or in a fixed location to produce a location-independent object identity memory or a location-dependent object representation. The training consisted of 5 trials that occurred either on one day (Massed) or over the course of 5 consecutive days (Spaced). The memory test was done in independent groups of animals either 24h or 7 days after the last training trial. In each test the animals were exposed to either a novel object, when trained with the objects in variable locations, or to a familiar object in a novel location, when trained with objects in fixed locations. The difference in time spent exploring the changed versus the familiar objects was used as a measure of recognition memory. For the object-identity-trained animals, spaced training produced clear evidence of recognition memory after both 24h and 7 days, but massed-training animals showed it only after 24h. In contrast, for the object-location-trained animals, recognition memory was evident after both retention intervals and with both training procedures. When objects were placed in variable locations for the two types of training and the test was done with a brand-new location, only the spaced-training animals showed recognition at 24h, but surprisingly, after 7 days, animals trained using both procedures were able to recognize the change, suggesting a post-training consolidation process. We suggest that the two training procedures trigger different neural mechanisms that may differ in the two segregated streams that process object information and that may consolidate differently. Copyright © 2013 Elsevier B.V. All rights reserved.

  7. The role of color information on object recognition: a review and meta-analysis.

    PubMed

    Bramão, Inês; Reis, Alexandra; Petersson, Karl Magnus; Faísca, Luís

    2011-09-01

    In this study, we systematically review the scientific literature on the effect of color on object recognition. Thirty-five independent experiments, comprising 1535 participants, were included in a meta-analysis. We found a moderate effect of color on object recognition (d=0.28). Specific effects of moderator variables were analyzed and we found that color diagnosticity is the factor with the greatest moderator effect on the influence of color in object recognition; studies using color diagnostic objects showed a significant color effect (d=0.43), whereas a marginal color effect was found in studies that used non-color diagnostic objects (d=0.18). The present study did not permit the drawing of specific conclusions about the moderator effect of the object recognition task; while the meta-analytic review showed that color information improves object recognition mainly in studies using naming tasks (d=0.36), the literature review revealed a large body of evidence showing positive effects of color information on object recognition in studies using a large variety of visual recognition tasks. We also found that color is important for the ability to recognize artifacts and natural objects, to recognize objects presented as types (line-drawings) or as tokens (photographs), and to recognize objects that are presented without surface details, such as texture or shadow. Taken together, the results of the meta-analysis strongly support the contention that color plays a role in object recognition. This suggests that the role of color should be taken into account in models of visual object recognition.

  8. Face Recognition Is Affected by Similarity in Spatial Frequency Range to a Greater Degree Than Within-Category Object Recognition

    ERIC Educational Resources Information Center

    Collin, Charles A.; Liu, Chang Hong; Troje, Nikolaus F.; McMullen, Patricia A.; Chaudhuri, Avi

    2004-01-01

    Previous studies have suggested that face identification is more sensitive to variations in spatial frequency content than object recognition, but none have compared how sensitive the 2 processes are to variations in spatial frequency overlap (SFO). The authors tested face and object matching accuracy under varying SFO conditions. Their results…

  9. Face Recognition Is Affected by Similarity in Spatial Frequency Range to a Greater Degree Than Within-Category Object Recognition

    ERIC Educational Resources Information Center

    Collin, Charles A.; Liu, Chang Hong; Troje, Nikolaus F.; McMullen, Patricia A.; Chaudhuri, Avi

    2004-01-01

    Previous studies have suggested that face identification is more sensitive to variations in spatial frequency content than object recognition, but none have compared how sensitive the 2 processes are to variations in spatial frequency overlap (SFO). The authors tested face and object matching accuracy under varying SFO conditions. Their results…

  10. An algorithm for recognition and localization of rotated and scaled objects

    NASA Technical Reports Server (NTRS)

    Peli, T.

    1981-01-01

    An algorithm for recognition and localization of objects, which is invariant to displacement and rotation, is extended to the recognition and localization of differently scaled, rotated, and displaced objects. The proposed algorithm provides an optimum way to find if a match exists between two objects that are scaled, rotated, and displaced, while the number of computations is of the same order as for equally scaled objects.

  11. Model-based object recognition in range imagery

    NASA Astrophysics Data System (ADS)

    Armbruster, Walter

    2009-09-01

    The paper formulates the mathematical foundations of object discrimination and object re-identification in range image sequences using Bayesian decision theory. Object discrimination determines the unique model corresponding to each scene object, while object re-identification finds the unique object in the scene corresponding to a given model. In the first case object identities are independent; in the second case at most one object exists having a given identity. Efficient analytical and numerical techniques for updating and maximizing the posterior distributions are introduced. Experimental results indicate to what extent a single range image of an object can be used for re-identifying this object in arbitrary scenes. Applications including the protection of commercial vessels against piracy are discussed.

  12. Object recognition through a multi-mode fiber

    NASA Astrophysics Data System (ADS)

    Takagi, Ryosuke; Horisaki, Ryoichi; Tanida, Jun

    2017-04-01

    We present a method of recognizing an object through a multi-mode fiber. A number of speckle patterns transmitted through a multi-mode fiber are provided to a classifier based on machine learning. We experimentally demonstrated binary classification of face and non-face targets based on the method. The measurement process of the experimental setup was random and nonlinear because a multi-mode fiber is a typical strongly scattering medium and any reference light was not used in our setup. Comparisons between three supervised learning methods, support vector machine, adaptive boosting, and neural network, are also provided. All of those learning methods achieved high accuracy rates at about 90% for the classification. The approach presented here can realize a compact and smart optical sensor. It is practically useful for medical applications, such as endoscopy. Also our study indicated a promising utilization of artificial intelligence, which has rapidly progressed, for reducing optical and computational costs in optical sensing systems.

  13. Object recognition through a multi-mode fiber

    NASA Astrophysics Data System (ADS)

    Takagi, Ryosuke; Horisaki, Ryoichi; Tanida, Jun

    2017-02-01

    We present a method of recognizing an object through a multi-mode fiber. A number of speckle patterns transmitted through a multi-mode fiber are provided to a classifier based on machine learning. We experimentally demonstrated binary classification of face and non-face targets based on the method. The measurement process of the experimental setup was random and nonlinear because a multi-mode fiber is a typical strongly scattering medium and any reference light was not used in our setup. Comparisons between three supervised learning methods, support vector machine, adaptive boosting, and neural network, are also provided. All of those learning methods achieved high accuracy rates at about 90% for the classification. The approach presented here can realize a compact and smart optical sensor. It is practically useful for medical applications, such as endoscopy. Also our study indicated a promising utilization of artificial intelligence, which has rapidly progressed, for reducing optical and computational costs in optical sensing systems.

  14. Characteristics of eye movements in 3-D object learning: comparison between within-modal and cross-modal object recognition.

    PubMed

    Ueda, Yoshiyuki; Saiki, Jun

    2012-01-01

    Recent studies have indicated that the object representation acquired during visual learning depends on the encoding modality during the test phase. However, the nature of the differences between within-modal learning (eg visual learning-visual recognition) and cross-modal learning (eg visual learning-haptic recognition) remains unknown. To address this issue, we utilised eye movement data and investigated object learning strategies during the learning phase of a cross-modal object recognition experiment. Observers informed of the test modality studied an unfamiliar visually presented 3-D object. Quantitative analyses showed that recognition performance was consistent regardless of rotation in the cross-modal condition, but was reduced when objects were rotated in the within-modal condition. In addition, eye movements during learning significantly differed between within-modal and cross-modal learning. Fixations were more diffused for cross-modal learning than in within-modal learning. Moreover, over the course of the trial, fixation durations became longer in cross-modal learning than in within-modal learning. These results suggest that the object learning strategies employed during the learning phase differ according to the modality of the test phase, and that this difference leads to different recognition performances.

  15. Parts and Relations in Young Children's Shape-Based Object Recognition

    ERIC Educational Resources Information Center

    Augustine, Elaine; Smith, Linda B.; Jones, Susan S.

    2011-01-01

    The ability to recognize common objects from sparse information about geometric shape emerges during the same period in which children learn object names and object categories. Hummel and Biederman's (1992) theory of object recognition proposes that the geometric shapes of objects have two components--geometric volumes representing major object…

  16. RecceMan: an interactive recognition assistance for image-based reconnaissance: synergistic effects of human perception and computational methods for object recognition, identification, and infrastructure analysis

    NASA Astrophysics Data System (ADS)

    El Bekri, Nadia; Angele, Susanne; Ruckhäberle, Martin; Peinsipp-Byma, Elisabeth; Haelke, Bruno

    2015-10-01

    This paper introduces an interactive recognition assistance system for imaging reconnaissance. This system supports aerial image analysts on missions during two main tasks: Object recognition and infrastructure analysis. Object recognition concentrates on the classification of one single object. Infrastructure analysis deals with the description of the components of an infrastructure and the recognition of the infrastructure type (e.g. military airfield). Based on satellite or aerial images, aerial image analysts are able to extract single object features and thereby recognize different object types. It is one of the most challenging tasks in the imaging reconnaissance. Currently, there are no high potential ATR (automatic target recognition) applications available, as consequence the human observer cannot be replaced entirely. State-of-the-art ATR applications cannot assume in equal measure human perception and interpretation. Why is this still such a critical issue? First, cluttered and noisy images make it difficult to automatically extract, classify and identify object types. Second, due to the changed warfare and the rise of asymmetric threats it is nearly impossible to create an underlying data set containing all features, objects or infrastructure types. Many other reasons like environmental parameters or aspect angles compound the application of ATR supplementary. Due to the lack of suitable ATR procedures, the human factor is still important and so far irreplaceable. In order to use the potential benefits of the human perception and computational methods in a synergistic way, both are unified in an interactive assistance system. RecceMan® (Reconnaissance Manual) offers two different modes for aerial image analysts on missions: the object recognition mode and the infrastructure analysis mode. The aim of the object recognition mode is to recognize a certain object type based on the object features that originated from the image signatures. The

  17. Object recognition by use of polarimetric phase-shifting digital holography.

    PubMed

    Nomura, Takanori; Javidi, Bahram

    2007-08-01

    Pattern recognition by use of polarimetric phase-shifting digital holography is presented. Using holography, the amplitude distribution and phase difference distribution between two orthogonal polarizations of three-dimensional (3D) or two-dimensional phase objects are obtained. This information contains both complex amplitude and polarimetric characteristics of the object, and it can be used for improving the discrimination capability of object recognition. Experimental results are presented to demonstrate the idea. To the best of our knowledge, this is the first report on 3D polarimetric recognition of objects using digital holography.

  18. Hierarchical Recognition Scheme for Human Facial Expression Recognition Systems

    PubMed Central

    Siddiqi, Muhammad Hameed; Lee, Sungyoung; Lee, Young-Koo; Khan, Adil Mehmood; Truc, Phan Tran Ho

    2013-01-01

    Over the last decade, human facial expressions recognition (FER) has emerged as an important research area. Several factors make FER a challenging research problem. These include varying light conditions in training and test images; need for automatic and accurate face detection before feature extraction; and high similarity among different expressions that makes it difficult to distinguish these expressions with a high accuracy. This work implements a hierarchical linear discriminant analysis-based facial expressions recognition (HL-FER) system to tackle these problems. Unlike the previous systems, the HL-FER uses a pre-processing step to eliminate light effects, incorporates a new automatic face detection scheme, employs methods to extract both global and local features, and utilizes a HL-FER to overcome the problem of high similarity among different expressions. Unlike most of the previous works that were evaluated using a single dataset, the performance of the HL-FER is assessed using three publicly available datasets under three different experimental settings: n-fold cross validation based on subjects for each dataset separately; n-fold cross validation rule based on datasets; and, finally, a last set of experiments to assess the effectiveness of each module of the HL-FER separately. Weighted average recognition accuracy of 98.7% across three different datasets, using three classifiers, indicates the success of employing the HL-FER for human FER. PMID:24316568

  19. Model-based 3-D object recognition using Hermite transform and homotopy techniques

    NASA Astrophysics Data System (ADS)

    Vaz, Richard F.; Cyganski, David; Wright, Charles R.

    1992-02-01

    This paper presents a new method for model-based object recognition and orientation determination which uses a single, comprehensive analytic object model representing the entirety of a suite of images of the object. In this way, object orientation and identity can be directly established from arbitrary views, even though these views are not related by any geometric image transformation. The approach is also applicable to other real and complex- sensed data, such as radar and thermal signatures. The object model is formed from 2-D Hermite function decompositions of an object image expanded about the angles of object rotation by Fourier series. A measure of error between the model and the acquired view is derived as an exact analytic expression, and is minimized over all values of the viewing angle by evaluation of a polynomial system of equations. The roots of this system are obtained via homotopy techniques, and directly provide object identity and orientation information. Results are given which illustrate the performance of this method for noisy real-world images acquired over a single viewing angle variation.

  20. Symbolic Play Connects to Language through Visual Object Recognition

    ERIC Educational Resources Information Center

    Smith, Linda B.; Jones, Susan S.

    2011-01-01

    Object substitutions in play (e.g. using a box as a car) are strongly linked to language learning and their absence is a diagnostic marker of language delay. Classic accounts posit a symbolic function that underlies both words and object substitutions. Here we show that object substitutions depend on developmental changes in visual object…

  1. How Does Using Object Names Influence Visual Recognition Memory?

    ERIC Educational Resources Information Center

    Richler, Jennifer J.; Palmeri, Thomas J.; Gauthier, Isabel

    2013-01-01

    Two recent lines of research suggest that explicitly naming objects at study influences subsequent memory for those objects at test. Lupyan (2008) suggested that naming "impairs" memory by a representational shift of stored representations of named objects toward the prototype (labeling effect). MacLeod, Gopie, Hourihan, Neary, and Ozubko (2010)…

  2. How Does Using Object Names Influence Visual Recognition Memory?

    ERIC Educational Resources Information Center

    Richler, Jennifer J.; Palmeri, Thomas J.; Gauthier, Isabel

    2013-01-01

    Two recent lines of research suggest that explicitly naming objects at study influences subsequent memory for those objects at test. Lupyan (2008) suggested that naming "impairs" memory by a representational shift of stored representations of named objects toward the prototype (labeling effect). MacLeod, Gopie, Hourihan, Neary, and Ozubko (2010)…

  3. Symbolic Play Connects to Language through Visual Object Recognition

    ERIC Educational Resources Information Center

    Smith, Linda B.; Jones, Susan S.

    2011-01-01

    Object substitutions in play (e.g. using a box as a car) are strongly linked to language learning and their absence is a diagnostic marker of language delay. Classic accounts posit a symbolic function that underlies both words and object substitutions. Here we show that object substitutions depend on developmental changes in visual object…

  4. Pattern recognition system and procedures

    NASA Technical Reports Server (NTRS)

    Nelson, G. D.; Serreyn, D. V.

    1972-01-01

    The ratio transformation technique is used to determine effective features as function of time in remote multiple sensing of crops and soils. The selection of quantizer parameters for a two-class recognition problem under the criteria of minimizing the probability of errors is also discussed.

  5. Combining depth and gray images for fast 3D object recognition

    NASA Astrophysics Data System (ADS)

    Pan, Wang; Zhu, Feng; Hao, Yingming

    2016-10-01

    Reliable and stable visual perception systems are needed for humanoid robotic assistants to perform complex grasping and manipulation tasks. The recognition of the object and its precise 6D pose are required. This paper addresses the challenge of detecting and positioning a textureless known object, by estimating its complete 6D pose in cluttered scenes. A 3D perception system is proposed in this paper, which can robustly recognize CAD models in cluttered scenes for the purpose of grasping with a mobile manipulator. Our approach uses a powerful combination of two different camera technologies, Time-Of-Flight (TOF) and RGB, to segment the scene and extract objects. Combining the depth image and gray image to recognize instances of a 3D object in the world and estimate their 3D poses. The full pose estimation process is based on depth images segmentation and an efficient shape-based matching. At first, the depth image is used to separate the supporting plane of objects from the cluttered background. Thus, cluttered backgrounds are circumvented and the search space is extremely reduced. And a hierarchical model based on the geometry information of a priori CAD model of the object is generated in the offline stage. Then using the hierarchical model we perform a shape-based matching in 2D gray images. Finally, we validate the proposed method in a number of experiments. The results show that utilizing depth and gray images together can reach the demand of a time-critical application and reduce the error rate of object recognition significantly.

  6. On the delay-dependent involvement of the hippocampus in object recognition memory.

    PubMed

    Hammond, Rebecca S; Tull, Laura E; Stackman, Robert W

    2004-07-01

    The role of the hippocampus in object recognition memory processes is unclear in the current literature. Conflicting results have been found in lesion studies of both primates and rodents. Procedural differences between studies, such as retention interval, may explain these discrepancies. In the present study, acute lidocaine administration was used to temporarily inactivate the hippocampus prior to training in the spontaneous object recognition task. Male C57BL/6J mice were administered bilateral lidocaine (4%, 0.5 microl/side) or aCSF (0.5 microl/side) directly into the CA1 region of the dorsal hippocampus 5 min prior to sample object training, and object recognition memory was tested after a short ( 5 min) or long (24 h) retention interval. There was no effect of intra-hippocampal lidocaine on the time needed for mice to accumulate sample object exploration, suggesting that inactivation of the hippocampus did not affect sample session activity or the motivation to explore objects. Lidocaine-treated mice exhibited impaired object recognition memory, measured as reduced novel object preference, after a 24 h but not a 5 min retention interval. These data support a delay-dependent role for the hippocampus in object recognition memory, an effect consistent with the results of hippocampal lesion studies conducted in rats. However, these data are also consistent with the view that the hippocampus is involved in object recognition memory regardless of retention interval, and that object recognition processes of parahippocampal structures (e.g., perirhinal cortex) are sufficient to support object recognition memory over short retention intervals.

  7. Shift- and scale-invariant recognition of contour objects with logarithmic radial harmonic filters.

    PubMed

    Moya, A; Esteve-Taboada, J J; García, J; Ferreira, C

    2000-10-10

    The phase-only logarithmic radial harmonic (LRH) filter has been shown to be suitable for scale-invariant block object recognition. However, an important set of objects is the collection of contour functions that results from a digital edge extraction of the original block objects. These contour functions have a constant width that is independent of the scale of the original object. Therefore, since the energy of the contour objects decreases more slowly with the scale factor than does the energy of the block objects, the phase-only LRH filter has difficulties in the recognition tasks when these contour objects are used. We propose a modified LRH filter that permits the realization of a shift- and scale-invariant optical recognition of contour objects. The modified LRH filter is a complex filter that compensates the energy variation resulting from the scaling of contour objects. Optical results validate the theory and show the utility of the newly proposed method.

  8. Higher-order neural network software for distortion invariant object recognition

    NASA Technical Reports Server (NTRS)

    Reid, Max B.; Spirkovska, Lilly

    1991-01-01

    The state-of-the-art in pattern recognition for such applications as automatic target recognition and industrial robotic vision relies on digital image processing. We present a higher-order neural network model and software which performs the complete feature extraction-pattern classification paradigm required for automatic pattern recognition. Using a third-order neural network, we demonstrate complete, 100 percent accurate invariance to distortions of scale, position, and in-plate rotation. In a higher-order neural network, feature extraction is built into the network, and does not have to be learned. Only the relatively simple classification step must be learned. This is key to achieving very rapid training. The training set is much smaller than with standard neural network software because the higher-order network only has to be shown one view of each object to be learned, not every possible view. The software and graphical user interface run on any Sun workstation. Results of the use of the neural software in autonomous robotic vision systems are presented. Such a system could have extensive application in robotic manufacturing.

  9. Statistical and neural network classifiers in model-based 3-D object recognition

    NASA Astrophysics Data System (ADS)

    Newton, Scott C.; Nutter, Brian S.; Mitra, Sunanda

    1991-02-01

    For autonomous machines equipped with vision capabilities and in a controlled environment 3-D model-based object identification methodologies will in general solve rigid body recognition problems. In an uncontrolled environment however several factors pose difficulties for correct identification. We have addressed the problem of 3-D object recognition using a number of methods including neural network classifiers and a Bayesian-like classifier for matching image data with model projection-derived data [1 21. Neural network classifiers used began operation as simple feature vector classifiers. However unmodelled signal behavior was learned with additional samples yielding great improvement in classification rates. The model analysis drastically shortened training time of both classification systems. In an environment where signal behavior is not accurately modelled two separate forms of learning give the systems the ability to update estimates of this behavior. Required of course are sufficient samples to learn this new information. Given sufficient information and a well-controlled environment identification of 3-D objects from a limited number of classes is indeed possible. 1.

  10. Automatic TLI recognition system, general description

    SciTech Connect

    Lassahn, G.D.

    1997-02-01

    This report is a general description of an automatic target recognition system developed at the Idaho National Engineering Laboratory for the Department of Energy. A user`s manual is a separate volume, Automatic TLI Recognition System, User`s Guide, and a programmer`s manual is Automatic TLI Recognition System, Programmer`s Guide. This system was designed as an automatic target recognition system for fast screening of large amounts of multi-sensor image data, based on low-cost parallel processors. This system naturally incorporates image data fusion, and it gives uncertainty estimates. It is relatively low cost, compact, and transportable. The software is easily enhanced to expand the system`s capabilities, and the hardware is easily expandable to increase the system`s speed. In addition to its primary function as a trainable target recognition system, this is also a versatile, general-purpose tool for image manipulation and analysis, which can be either keyboard-driven or script-driven. This report includes descriptions of three variants of the computer hardware, a description of the mathematical basis if the training process, and a description with examples of the system capabilities.

  11. Representational dynamics of object recognition: Feedforward and feedback information flows.

    PubMed

    Goddard, Erin; Carlson, Thomas A; Dermody, Nadene; Woolgar, Alexandra

    2016-03-01

    Object perception involves a range of visual and cognitive processes, and is known to include both a feedfoward flow of information from early visual cortical areas to higher cortical areas, along with feedback from areas such as prefrontal cortex. Previous studies have found that low and high spatial frequency information regarding object identity may be processed over different timescales. Here we used the high temporal resolution of magnetoencephalography (MEG) combined with multivariate pattern analysis to measure information specifically related to object identity in peri-frontal and peri-occipital areas. Using stimuli closely matched in their low-level visual content, we found that activity in peri-occipital cortex could be used to decode object identity from ~80ms post stimulus onset, and activity in peri-frontal cortex could also be used to decode object identity from a later time (~265ms post stimulus onset). Low spatial frequency information related to object identity was present in the MEG signal at an earlier time than high spatial frequency information for peri-occipital cortex, but not for peri-frontal cortex. We additionally used Granger causality analysis to compare feedforward and feedback influences on representational content, and found evidence of both an early feedfoward flow and later feedback flow of information related to object identity. We discuss our findings in relation to existing theories of object processing and propose how the methods we use here could be used to address further questions of the neural substrates underlying object perception.

  12. Human hand descriptions and gesture recognition for object manipulation.

    PubMed

    Cobos, Salvador; Ferre, Manuel; Sánchez-Urán, M Ángel; Ortego, Javier; Aracil, Rafael

    2010-06-01

    This work focuses on obtaining realistic human hand models that are suitable for manipulation tasks. A 24 degrees of freedom (DoF) kinematic model of the human hand is defined. The model reasonably satisfies realism requirements in simulation and movement. To achieve realism, intra- and inter-finger constraints are obtained. The design of the hand model with 24 DoF is based upon a morphological, physiological and anatomical study of the human hand. The model is used to develop a gesture recognition procedure that uses principal components analysis (PCA) and discriminant functions. Two simplified hand descriptions (nine and six DoF) have been developed in accordance with the constraints obtained previously. The accuracy of the simplified models is almost 5% for the nine DoF hand description and 10% for the six DoF hand description. Finally, some criteria are defined by which to select the hand description best suited to the features of the manipulation task.

  13. Disturbances of novel object exploration and recognition in a chronic ketamine mouse model of schizophrenia.

    PubMed

    Hauser, Maria Jelena; Isbrandt, Dirk; Roeper, Jochen

    2017-08-14

    Schizophrenia is a chronic and devastating disease with an overall lifetime risk of 1%. While positive symptoms of schizophrenia such as hallucinations and delusions are reduced by antipsychotic medication based on the inhibition of type 2 dopaminergic receptors (D2R), negative symptoms (e.g. reduced motivation) and cognitive symptoms (e.g. impaired working memory) of schizophrenia are not effectively treated by current medication. This dichotomy might arise in part because of our limited understanding of the pathophysiology of negative and cognitive symptoms in schizophrenia. In addition to genetic approaches, chronic systemic application of NMDA inhibitors such as ketamine have been used to generate rodent models, which displayed several relevant endophenotypes related to negative and cognitive symptoms and might thus facilitate mechanistic studies into the underlying pathophysiology. In this context, previous behavioral testing identified impairments in novel object recognition memory as a key feature in chronic NMDA-inhibitor schizophrenia rodent models. Using a chronic ketamine mouse model, we have however identified are more complex behavioral phenotype including deficits in novel space and novel object exploration in combination deficits in short-term novel object recognition memory. These impairments in novelty discrimination are in line with prefrontal and hippocampal reductions in parvalbumin-expression as well as reduced expression of the early immediate gene c-fos after novel-object exploration in hippocampal areas in our model. Our results indicate that adult C57Bl6N mice chronically treated with ketamine display combined impairments in novelty exploration and recognition, which might represent both motivational (negative) and cognitive symptoms of schizophrenia. Copyright © 2017 Elsevier B.V. All rights reserved.

  14. Robust model-based object recognition using a dual-hierarchy graph

    NASA Astrophysics Data System (ADS)

    Weiss, Isaac

    2012-05-01

    We present a general purpose, inherently robust system for object representation and recognition. The system is model-based and knowledge-based, with knowledge derived from analysis of objects and images, unlike many of the current methods which rely on generic statistical inference. This knowledge is intrinsic to the objects themselves, based on geometric and semantic relations among objects. Therefor the system is insensitive to external interferences such as viewpoint changes (scale, pose etc.), illumination changes, occlusion, shadows, sensor noise etc. It also handles variability in the object itself, e.g. articulation or camouflage. We represent all available models in a graph containing two independent but interlocking hierarchies. One of these intrinsic hierarchies is based on parts, e.g. a truck has a cabin, a trunk, wheels etc. The other hierarchy we call the "Level of Abstraction (LOA), e.g. a vehicle is more abstract than a truck, a rectangle is more abstract than a door. This enables us to represent and recognize generic objects just as easily as specific ones. A new algorithm for traversing our graph, combining the advantages of both top-down and bottom-up strategies, has been implemented.

  15. The Use of Grouping in Visual Object Recognition

    DTIC Science & Technology

    1988-10-01

    that object. 44 Pol i"on I Polyon 2 Polygon 3 Figure 3.7: Three randomly chosen, convex polygons. Since we assume that any object appears at randomly...I Polyon 2 Polygon 3 DISTAICE DISTRICE Figure 5.4: On the left, the probability distribution which GROPER uses for the expected distance between

  16. Resolving human object recognition in space and time

    PubMed Central

    Cichy, Radoslaw Martin; Pantazis, Dimitrios; Oliva, Aude

    2014-01-01

    A comprehensive picture of object processing in the human brain requires combining both spatial and temporal information about brain activity. Here, we acquired human magnetoencephalography (MEG) and functional magnetic resonance imaging (fMRI) responses to 92 object images. Multivariate pattern classification applied to MEG revealed the time course of object processing: whereas individual images were discriminated by visual representations early, ordinate and superordinate category levels emerged relatively later. Using representational similarity analysis, we combine human fMRI and MEG to show content-specific correspondence between early MEG responses and primary visual cortex (V1), and later MEG responses and inferior temporal (IT) cortex. We identified transient and persistent neural activities during object processing, with sources in V1 and IT., Finally, human MEG signals were correlated to single-unit responses in monkey IT. Together, our findings provide an integrated space- and time-resolved view of human object categorization during the first few hundred milliseconds of vision. PMID:24464044

  17. Stereo disparity facilitates view generalization during shape recognition for solid multipart objects.

    PubMed

    Cristino, Filipe; Davitt, Lina; Hayward, William G; Leek, E Charles

    2015-01-01

    Current theories of object recognition in human vision make different predictions about whether the recognition of complex, multipart objects should be influenced by shape information about surface depth orientation and curvature derived from stereo disparity. We examined this issue in five experiments using a recognition memory paradigm in which observers (N = 134) memorized and then discriminated sets of 3D novel objects at trained and untrained viewpoints under either mono or stereo viewing conditions. In order to explore the conditions under which stereo-defined shape information contributes to object recognition we systematically varied the difficulty of view generalization by increasing the angular disparity between trained and untrained views. In one series of experiments, objects were presented from either previously trained views or untrained views rotated (15°, 30°, or 60°) along the same plane. In separate experiments we examined whether view generalization effects interacted with the vertical or horizontal plane of object rotation across 40° viewpoint changes. The results showed robust viewpoint-dependent performance costs: Observers were more efficient in recognizing learned objects from trained than from untrained views, and recognition was worse for extrapolated than for interpolated untrained views. We also found that performance was enhanced by stereo viewing but only at larger angular disparities between trained and untrained views. These findings show that object recognition is not based solely on 2D image information but that it can be facilitated by shape information derived from stereo disparity.

  18. Zero-Copy Objects System

    NASA Technical Reports Server (NTRS)

    Burleigh, Scott C.

    2011-01-01

    Zero-Copy Objects System software enables application data to be encapsulated in layers of communication protocol without being copied. Indirect referencing enables application source data, either in memory or in a file, to be encapsulated in place within an unlimited number of protocol headers and/or trailers. Zero-copy objects (ZCOs) are abstract data access representations designed to minimize I/O (input/output) in the encapsulation of application source data within one or more layers of communication protocol structure. They are constructed within the heap space of a Simple Data Recorder (SDR) data store to which all participating layers of the stack must have access. Each ZCO contains general information enabling access to the core source data object (an item of application data), together with (a) a linked list of zero or more specific extents that reference portions of this source data object, and (b) linked lists of protocol header and trailer capsules. The concatenation of the headers (in ascending stack sequence), the source data object extents, and the trailers (in descending stack sequence) constitute the transmitted data object constructed from the ZCO. This scheme enables a source data object to be encapsulated in a succession of protocol layers without ever having to be copied from a buffer at one layer of the protocol stack to an encapsulating buffer at a lower layer of the stack. For large source data objects, the savings in copy time and reduction in memory consumption may be considerable.

  19. Effects of varying stimulus size on object recognition in pigeons.

    PubMed

    Peissig, Jessie J; Kirkpatrick, Kimberly; Young, Michael E; Wasserman, Edward E; Biederman, Irving

    2006-10-01

    The authors investigated the pigeon's ability to generalize object discrimination performance to smaller and larger versions of trained objects. In Experiment 1, they taught pigeons with line drawings of multipart objects and later tested the birds with both larger and smaller drawings. The pigeons exhibited significant generalization to new sizes, although they did show systematic performance decrements as the new size deviated from the original. In Experiment 2, the authors tested both linear and exponential size changes of computer-rendered basic shapes to determine which size transformation produced equivalent performance for size increases and decreases. Performance was more consistent with logarithmic than with linear scaling of size. This finding was supported in Experiment 3. Overall, the experiments suggest that the pigeon encodes size as a feature of objects and that the representation of size is most likely logarithmic.

  20. Artificial neural networks and model-based recognition of 3-D objects from 2-D images

    NASA Astrophysics Data System (ADS)

    Chao, Chih-Ho; Dhawan, Atam P.

    1992-09-01

    A computer vision system is developed for 3-D object recognition using artificial neural networks and a knowledge-based top-down feedback analysis system. This computer vision system can adequately analyze an incomplete edge map provided by a low-level processor for 3-D representation and recognition using key features. The key features are selected using a priority assignment and then used in an artificial neural network for matching with model key features. The result of such matching is utilized in generating the model-driven top-down feedback analysis. From the incomplete edge map we try to pick a candidate pattern utilizing the key feature priority assignment. The highest priority is given for the most connected node and associated features. The features are space invariant structures and sets of orientation for edge primitives. These features are now mapped into real numbers. A Hopfield network is then applied with two levels of matching to reduce the search time. The first match is to choose the class of possible model, the second match is then to find the model closest to the data patterns. This model is then rotated in 3-D to find the best match with the incomplete edge patterns and to provide the additional features in 3-D. In the case of multiple objects, a dynamically interconnected search strategy is designed to recognize objects using one pattern at a time. This strategy is also useful in recognizing occluded objects. The experimental results presented show the capability and effectiveness of this system.

  1. Dual-Hierarchy Graph Method for Object Indexing and Recognition

    DTIC Science & Technology

    2014-07-01

    changes, occlusion, shadows, sensor noise etc. It also handles variability in the object itself, e.g. articulation or camouflage. All available models...changes (pose, scale etc.), illumination changes, occlusion, shadows, sensor noise etc. It also handles variability in the object itself, e.g...intrinsic hierarchies is based on parts, e.g. a truck has a cabin , a trunk, wheels etc. The other hierarchy we call the "Level of Abstraction” (LOA), e.g. a

  2. Mechanisms and neural basis of object and pattern recognition: a study with chess experts.

    PubMed

    Bilalić, Merim; Langner, Robert; Erb, Michael; Grodd, Wolfgang

    2010-11-01

    Comparing experts with novices offers unique insights into the functioning of cognition, based on the maximization of individual differences. Here we used this expertise approach to disentangle the mechanisms and neural basis behind two processes that contribute to everyday expertise: object and pattern recognition. We compared chess experts and novices performing chess-related and -unrelated (visual) search tasks. As expected, the superiority of experts was limited to the chess-specific task, as there were no differences in a control task that used the same chess stimuli but did not require chess-specific recognition. The analysis of eye movements showed that experts immediately and exclusively focused on the relevant aspects in the chess task, whereas novices also examined irrelevant aspects. With random chess positions, when pattern knowledge could not be used to guide perception, experts nevertheless maintained an advantage. Experts' superior domain-specific parafoveal vision, a consequence of their knowledge about individual domain-specific symbols, enabled improved object recognition. Functional magnetic resonance imaging corroborated this differentiation between object and pattern recognition and showed that chess-specific object recognition was accompanied by bilateral activation of the occipitotemporal junction, whereas chess-specific pattern recognition was related to bilateral activations in the middle part of the collateral sulci. Using the expertise approach together with carefully chosen controls and multiple dependent measures, we identified object and pattern recognition as two essential cognitive processes in expert visual cognition, which may also help to explain the mechanisms of everyday perception.

  3. Selecting and implementing a voice recognition system.

    PubMed

    Wheeler, S; Cassimus, G C

    1999-01-01

    A single radiology department serves the three separate organizations that comprise Emory Healthcare in Atlanta--three separate hospitals, the Emory Clinic and the Emory University School of Medicine. In 1996, the chairman of Emory Healthcare issued a mandate to the radiology department to decrease its report turnaround time, provide better service and increase customer satisfaction. The area where the greatest effect could be made without involving the transcription area was the "exam complete to dictate" piece of the reporting process. A committee investigating voice recognition systems established an essential criteria for potential vendors--to be able to download patient scheduling and demographic information from the existing RIS to the new system. Second, the system had to be flexible and straightforward for doctors to learn. It must have a word processing package for easy report correction and editing, and a microphone that would rewind and correct dictation before recognition took place. To keep capital costs low for the pilot, the committee opted for server recognition rather than purchase the expensive workstations necessary for real-time recognition. A switch was made later to real-time recognition. PACS and voice recognition have proven to be highly complementary. Most importantly, the new system has had a tremendous impact on turnaround time in the "dictate to final" phase. Once in the 30-hour range, 65 percent of the reports are now turned around in less than 15 minutes, 80 percent in less than 30 minutes, and 90 percent in less than an hour.

  4. Fast and flexible 3D object recognition solutions for machine vision applications

    NASA Astrophysics Data System (ADS)

    Effenberger, Ira; Kühnle, Jens; Verl, Alexander

    2013-03-01

    In automation and handling engineering, supplying work pieces between different stages along the production process chain is of special interest. Often the parts are stored unordered in bins or lattice boxes and hence have to be separated and ordered for feeding purposes. An alternative to complex and spacious mechanical systems such as bowl feeders or conveyor belts, which are typically adapted to the parts' geometry, is using a robot to grip the work pieces out of a bin or from a belt. Such applications are in need of reliable and precise computer-aided object detection and localization systems. For a restricted range of parts, there exists a variety of 2D image processing algorithms that solve the recognition problem. However, these methods are often not well suited for the localization of randomly stored parts. In this paper we present a fast and flexible 3D object recognizer that localizes objects by identifying primitive features within the objects. Since technical work pieces typically consist to a substantial degree of geometric primitives such as planes, cylinders and cones, such features usually carry enough information in order to determine the position of the entire object. Our algorithms use 3D best-fitting combined with an intelligent data pre-processing step. The capability and performance of this approach is shown by applying the algorithms to real data sets of different industrial test parts in a prototypical bin picking demonstration system.

  5. Design and implementation of knowledge-based framework for ground objects recognition in remote sensing images

    NASA Astrophysics Data System (ADS)

    Chen, Shaobin; Ding, Mingyue; Cai, Chao; Fu, Xiaowei; Sun, Yue; Chen, Duo

    2009-10-01

    The advance of image processing makes knowledge-based automatic image interpretation much more realistic than ever. In the domain of remote sensing image processing, the introduction of knowledge enhances the confidence of recognition of typical ground objects. There are mainly two approaches to employ knowledge: the first one is scattering knowledge in concrete program and relevant knowledge of ground objects are fixed by programming; the second is systematically storing knowledge in knowledge base to offer a unified instruction for each object recognition procedure. In this paper, a knowledge-based framework for ground objects recognition in remote sensing image is proposed. This framework takes the second means for using knowledge with a hierarchical architecture. The recognition of typical airport demonstrated the feasibility of the proposed framework.

  6. The resilience of object predictions: Early recognition across viewpoints and exemplars

    PubMed Central

    Cheung, Olivia S.; Bar, Moshe

    2013-01-01

    Recognition of everyday objects can be facilitated by top-down predictions. We have proposed that these predictions are derived from rudimentary shape information, or gist, extracted rapidly from low spatial frequencies (LSFs) in the image (Bar, 2003). Because of the coarse nature of LSF representations, we hypothesize here that such predictions can accommodate changes in viewpoint as well as facilitate the recognition of visually similar objects. In a repetition-priming task, we indeed observed significant facilitation of target recognition that was primed by LSF objects across moderate viewpoint changes, as well as across visually similar exemplars. These results suggest that the LSF representations are specific enough to activate accurate predictions, yet flexible enough to overcome small changes in visual appearance. Such gist representations facilitate object recognition by accommodating changes in visual appearance due to viewing conditions and help to generalize from familiar to novel exemplars. PMID:24234168

  7. It’s all connected: Pathways in visual object recognition and early noun learning

    PubMed Central

    Smith, Linda B.

    2013-01-01

    A developmental pathway may be defined as the route, or chain of events, through which a new structure or function forms. For many human behaviors, including object name learning and visual object recognition, these pathways are often complex, multi-causal and include unexpected dependencies. This paper presents three principles of development that suggest the value of a developmental psychology that explicitly seeks to trace these pathways and uses empirical evidence on developmental dependencies between motor development, action on objects, visual object recognition and object name learning in 12 to 24 month old infants to make the case. The paper concludes with a consideration of the theoretical implications of this approach. PMID:24320634

  8. Implicit encoding of extrinsic object properties in stored representations mediating recognition: evidence from shadow-specific repetition priming.

    PubMed

    Leek, E Charles; Davitt, Lina I; Cristino, Filipe

    2015-03-01

    This study investigated whether, and under what conditions, stored shape representations mediating recognition encode extrinsic object properties that vary according to viewing conditions. This was examined in relation to cast shadow. Observers (N = 90) first memorised a subset of 3D multi-part novel objects from a limited range of viewpoints rendered with either no shadow, object internal shadow, or both object internal and external (ground) plane shadow. During a subsequent test phase previously memorised targets were discriminated from visually similar distractors across learned and novel views following brief presentation of a same-shape masked prime. The primes contained either matching or mismatching shadow rendering from the training condition. The results showed a recognition advantage for objects memorised with object internal shadow. In addition, objects encoded with internal shadow were primed more strongly by matching internal shadow primes, than by same shape primes with either no shadow or both object internal and external (ground) shadow. This pattern of priming effects generalises to previously unseen views of targets rendered with object internal shadow. The results suggest that the object recognition system contains a level of stored representation at which shape and the extrinsic object property of cast shadow are bound. We propose that this occurs when cast shadow cannot be discounted during perception on the basis of external cues to the scene lighting model.

  9. Dissociations in the effect of delay on object recognition: evidence for an associative model of recognition memory.

    PubMed

    Tam, Shu K E; Robinson, Jasper; Jennings, Dómhnall J; Bonardi, Charlotte

    2014-01-01

    Rats were administered 3 versions of an object recognition task: In the spontaneous object recognition task (SOR) animals discriminated between a familiar object and a novel object; in the temporal order task they discriminated between 2 familiar objects, 1 of which had been presented more recently than the other; and, in the object-in-place task, they discriminated among 4 previously presented objects, 2 of which were presented in the same locations as in preexposure and 2 in different but familiar locations. In each task animals were tested at 2 delays (5 min and 2 hr) between the sample and test phases in the SOR and object-in-place task, and between the 2 sample phases in the temporal order task. Performance in the SOR was poorer with the longer delay, whereas in the temporal order task performance improved with delay. There was no effect of delay on object-in-place performance. In addition the performance of animals with neurotoxic lesions of the dorsal hippocampus was selectively impaired in the object-in-place task at the longer delay. These findings are interpreted within the framework of Wagner's (1981) model of memory.

  10. Practical vision based degraded text recognition system

    NASA Astrophysics Data System (ADS)

    Mohammad, Khader; Agaian, Sos; Saleh, Hani

    2011-02-01

    Rapid growth and progress in the medical, industrial, security and technology fields means more and more consideration for the use of camera based optical character recognition (OCR) Applying OCR to scanned documents is quite mature, and there are many commercial and research products available on this topic. These products achieve acceptable recognition accuracy and reasonable processing times especially with trained software, and constrained text characteristics. Even though the application space for OCR is huge, it is quite challenging to design a single system that is capable of performing automatic OCR for text embedded in an image irrespective of the application. Challenges for OCR systems include; images are taken under natural real world conditions, Surface curvature, text orientation, font, size, lighting conditions, and noise. These and many other conditions make it extremely difficult to achieve reasonable character recognition. Performance for conventional OCR systems drops dramatically as the degradation level of the text image quality increases. In this paper, a new recognition method is proposed to recognize solid or dotted line degraded characters. The degraded text string is localized and segmented using a new algorithm. The new method was implemented and tested using a development framework system that is capable of performing OCR on camera captured images. The framework allows parameter tuning of the image-processing algorithm based on a training set of camera-captured text images. Novel methods were used for enhancement, text localization and the segmentation algorithm which enables building a custom system that is capable of performing automatic OCR which can be used for different applications. The developed framework system includes: new image enhancement, filtering, and segmentation techniques which enabled higher recognition accuracies, faster processing time, and lower energy consumption, compared with the best state of the art published

  11. Automatic TLI recognition system beta prototype testing

    SciTech Connect

    Lassahn, G.D.

    1996-06-01

    This report describes the beta prototype automatic target recognition system ATR3, and some performance tests done with this system. This is a fully operational system, with a high computational speed. It is useful for findings any kind of target in digitized image data, and as a general purpose image analysis tool.

  12. Do Simultaneously Viewed Objects Influence Scene Recognition Individually or as Groups? Two Perceptual Studies

    PubMed Central

    Gagne, Christopher R.; MacEvoy, Sean P.

    2014-01-01

    The ability to quickly categorize visual scenes is critical to daily life, allowing us to identify our whereabouts and to navigate from one place to another. Rapid scene categorization relies heavily on the kinds of objects scenes contain; for instance, studies have shown that recognition is less accurate for scenes to which incongruent objects have been added, an effect usually interpreted as evidence of objects' general capacity to activate semantic networks for scene categories they are statistically associated with. Essentially all real-world scenes contain multiple objects, however, and it is unclear whether scene recognition draws on the scene associations of individual objects or of object groups. To test the hypothesis that scene recognition is steered, at least in part, by associations between object groups and scene categories, we asked observers to categorize briefly-viewed scenes appearing with object pairs that were semantically consistent or inconsistent with the scenes. In line with previous results, scenes were less accurately recognized when viewed with inconsistent versus consistent pairs. To understand whether this reflected individual or group-level object associations, we compared the impact of pairs composed of mutually related versus unrelated objects; i.e., pairs, which, as groups, had clear associations to particular scene categories versus those that did not. Although related and unrelated object pairs equally reduced scene recognition accuracy, unrelated pairs were consistently less capable of drawing erroneous scene judgments towards scene categories associated with their individual objects. This suggests that scene judgments were influenced by the scene associations of object groups, beyond the influence of individual objects. More generally, the fact that unrelated objects were as capable of degrading categorization accuracy as related objects, while less capable of generating specific alternative judgments, indicates that the process

  13. Kappa Opioid Receptor-Mediated Disruption of Novel Object Recognition: Relevance for Psychostimulant Treatment

    PubMed Central

    Paris, Jason J.; Reilley, Kate J.; McLaughlin, Jay P.

    2012-01-01

    Kappa opioid receptor (KOR) agonists are potentially valuable as therapeutics for the treatment of psychostimulant reward as they suppress dopamine signaling in reward circuitry to repress drug seeking behavior. However, KOR agonists are also associated with sedation and cognitive dysfunction. The extent to which learning and memory disruption or hypolocomotion underlie KOR agonists’ role in counteracting the rewarding effects of psychostimulants is of interest. C57BL/6J mice were pretreated with vehicle (saline, 0.9%), the KOR agonist (trans)-3,4-dichloro-N-methyl-N-[2-(1- pyrrolidinyl)-cyclohexyl] benzeneacetamide (U50,488), or the peripherally-restricted agonist D-Phe-D-Phe-D-lle-D-Arg- NH2 (ffir-NH2), through central (i.c.v.) or peripheral (i.p.) routes of administration. Locomotor activity was assessed via activity monitoring chambers and rotorod. Cognitive performance was assessed in a novel object recognition task. Prolonged hypolocomotion was observed following administration of 1.0 and 10.0, but not 0.3 mg/kg U50,488. Central, but not peripheral, administration of ffir-NH2 (a KOR agonist that does not cross the blood-brain barrier) also reduced motor behavior. Systemic pretreatment with the low dose of U50,488 (0.3 mg/kg, i.p.) significantly impaired performance in the novel object recognition task. Likewise, ffir-NH2 significantly reduced novel object recognition after central (i.c.v.), but not peripheral (i.p.), administration. U50,488- and ffir-NH2-mediated deficits in novel object recognition were prevented by pretreatment with KOR antagonists. Cocaine-induced conditioned place preference was subsequently assessed and was reduced by pretreatment with U50,488 (0.3 mg/kg, i.p.). Together, these results suggest that the activation of centrally-located kappa opioid receptors may induce cognitive and mnemonic disruption independent of hypolocomotor effects which may contribute to the KOR-mediated suppression of psychostimulant reward. PMID:22900234

  14. Object Recognition and Attention to Object Components by Preschool Children and 4-Month-Old Infants.

    ERIC Educational Resources Information Center

    Haaf, Robert A.

    2003-01-01

    This study investigated attention to and recognition of components in compound stimuli among infants and preschoolers. Oddity tasks with preschoolers and familiarization/novelty-preference tasks with infants demonstrated successful discrimination among stimuli components on basis of edge property information. Matching tasks with preschoolers and…

  15. Dissociating the Effects of Angular Disparity and Image Similarity in Mental Rotation and Object Recognition

    ERIC Educational Resources Information Center

    Cheung, Olivia S.; Hayward, William G.; Gauthier, Isabel

    2009-01-01

    Performance is often impaired linearly with increasing angular disparity between two objects in tasks that measure mental rotation or object recognition. But increased angular disparity is often accompanied by changes in the similarity between views of an object, confounding the impact of the two factors in these tasks. We examined separately the…

  16. Complementary Hemispheric Asymmetries in Object Naming and Recognition: A Voxel-Based Correlational Study

    ERIC Educational Resources Information Center

    Acres, K.; Taylor, K. I.; Moss, H. E.; Stamatakis, E. A.; Tyler, L. K.

    2009-01-01

    Cognitive neuroscientific research proposes complementary hemispheric asymmetries in naming and recognising visual objects, with a left temporal lobe advantage for object naming and a right temporal lobe advantage for object recognition. Specifically, it has been proposed that the left inferior temporal lobe plays a mediational role linking…

  17. Complementary Hemispheric Asymmetries in Object Naming and Recognition: A Voxel-Based Correlational Study

    ERIC Educational Resources Information Center

    Acres, K.; Taylor, K. I.; Moss, H. E.; Stamatakis, E. A.; Tyler, L. K.

    2009-01-01

    Cognitive neuroscientific research proposes complementary hemispheric asymmetries in naming and recognising visual objects, with a left temporal lobe advantage for object naming and a right temporal lobe advantage for object recognition. Specifically, it has been proposed that the left inferior temporal lobe plays a mediational role linking…

  18. Dissociating the Effects of Angular Disparity and Image Similarity in Mental Rotation and Object Recognition

    ERIC Educational Resources Information Center

    Cheung, Olivia S.; Hayward, William G.; Gauthier, Isabel

    2009-01-01

    Performance is often impaired linearly with increasing angular disparity between two objects in tasks that measure mental rotation or object recognition. But increased angular disparity is often accompanied by changes in the similarity between views of an object, confounding the impact of the two factors in these tasks. We examined separately the…

  19. Remote object recognition by analysis of surface structure

    NASA Astrophysics Data System (ADS)

    Wurster, J.; Stark, H.; Olsen, E. T.; Kogler, K.

    1995-06-01

    We present a new algorithm for the discrimination of remote objects by their surface structure. Starting from a range-azimuth profile function, we formulate a range-azimuth matrix whose largest eigenvalues are used as discriminating features to separate object classes. A simpler, competing algorithm uses the number of sign changes in the range-azimuth profile function to discriminate among classes. Whereas both algorithms work well on noiseless data, an experiment involving real data shows that the eigenvalue method is far more robust with respect to noise than is the sign-change method. Two well-known methods based on surface structure, variance, and fractal dimension were also tested on real data. Neither method furnished the aspect invariance and the discriminability of the eigenvalue method.

  20. The relationship between change detection and recognition of centrally attended objects in motion pictures.

    PubMed

    Angelone, Bonnie L; Levin, Daniel T; Simons, Daniel J

    2003-01-01

    Observers typically detect changes to central objects more readily than changes to marginal objects, but they sometimes miss changes to central, attended objects as well. However, even if observers do not report such changes, they may be able to recognize the changed object. In three experiments we explored change detection and recognition memory for several types of changes to central objects in motion pictures. Observers who failed to detect a change still performed at above chance levels on a recognition task in almost all conditions. In addition, observers who detected the change were no more accurate in their recognition than those who did not detect the change. Despite large differences in the detectability of changes across conditions, those observers who missed the change did not vary in their ability to recognize the changing object.

  1. Category-specific interference of object recognition with biological motion perception.

    PubMed

    Wittinghofer, Karin; de Lussanet, Marc H E; Lappe, Markus

    2010-11-24

    The rapid and detailed recognition of human action from point-light displays is a remarkable ability and very robust against masking by motion signals. However, recognition of biological motion is strongly impaired when the typical point lights are replaced by pictures of complex objects. In a reaction time task and a detection in noise task, we asked subjects to decide if the walking direction is forward or backward. We found that complex objects as local elements impaired performance. When we compared different object categories, we found that human shapes as local objects gave more impairment than any other tested object category. Inverting or scrambling the human shapes restored the performance of walking perception. These results demonstrate an interference between object perception and biological motion recognition caused by shared processing capacities.

  2. Dissociating the effects of angular disparity and image similarity in mental rotation and object recognition.

    PubMed

    Cheung, Olivia S; Hayward, William G; Gauthier, Isabel

    2009-10-01

    Performance is often impaired linearly with increasing angular disparity between two objects in tasks that measure mental rotation or object recognition. But increased angular disparity is often accompanied by changes in the similarity between views of an object, confounding the impact of the two factors in these tasks. We examined separately the effects of angular disparity and image similarity on handedness (to test mental rotation) and identity (to test object recognition) judgments with 3-D novel objects. When similarity was approximately equated, an effect of angular disparity was only found for handedness but not identity judgments. With a fixed angular disparity, performance was better for similar than dissimilar image pairs in both tasks, with a larger effect for identity than handedness judgments. Our results suggest that mental rotation involves mental transformation procedures that depend on angular disparity, but that object recognition is predominately dependent on the similarity of image features.

  3. Object-oriented recognition of high-resolution remote sensing image

    NASA Astrophysics Data System (ADS)

    Wang, Yongyan; Li, Haitao; Chen, Hong; Xu, Yuannan

    2016-01-01

    With the development of remote sensing imaging technology and the improvement of multi-source image's resolution in satellite visible light, multi-spectral and hyper spectral , the high resolution remote sensing image has been widely used in various fields, for example military field, surveying and mapping, geophysical prospecting, environment and so forth. In remote sensing image, the segmentation of ground targets, feature extraction and the technology of automatic recognition are the hotspot and difficulty in the research of modern information technology. This paper also presents an object-oriented remote sensing image scene classification method. The method is consist of vehicles typical objects classification generation, nonparametric density estimation theory, mean shift segmentation theory, multi-scale corner detection algorithm, local shape matching algorithm based on template. Remote sensing vehicles image classification software system is designed and implemented to meet the requirements .

  4. An optimal sensing strategy for recognition and localization of 3-D natural quadric objects

    NASA Technical Reports Server (NTRS)

    Lee, Sukhan; Hahn, Hernsoo

    1991-01-01

    An optimal sensing strategy for an optical proximity sensor system engaged in the recognition and localization of 3-D natural quadric objects is presented. The optimal sensing strategy consists of the selection of an optimal beam orientation and the determination of an optimal probing plane that compose an optimal data collection operation known as an optimal probing. The decision of an optimal probing is based on the measure of discrimination power of a cluster of surfaces on a multiple interpretation image (MII), where the measure of discrimination power is defined in terms of a utility function computing the expected number of interpretations that can be pruned out by a probing. An object representation suitable for active sensing based on a surface description vector (SDV) distribution graph and hierarchical tables is presented. Experimental results are shown.

  5. 3D Object Recognition: Symmetry and Virtual Views

    DTIC Science & Technology

    1992-12-01

    NAME(S) AND ADDRESS(ES) 8. PERFORMING ORGANIZATIONI Artificial Intelligence Laboratory REPORT NUMBER 545 Technology Square AIM 1409 Cambridge... ARTIFICIAL INTELLIGENCE LABORATORY and CENTER FOR BIOLOGICAL AND COMPUTATIONAL LEARNING A.I. Memo No. 1409 December 1992 C.B.C.L. Paper No. 76 3D Object...research done within the Center for Biological and Computational Learning in the Department of Brain and Cognitive Sciences, and at the Artificial

  6. Informative Feature Selection for Object Recognition via Sparse PCA

    DTIC Science & Technology

    2011-04-07

    the BMW database [17] are used for training. For each image pair in SfM, SURF features are deemed informative if the consensus of the corresponding...observe that the first two sparse PVs are sufficient for selecting in- formative features that lie on the foreground objects in the BMW database (as... BMW ) database [17]. The database consists of multiple-view images of 20 landmark buildings on the Berkeley campus. For each building, wide-baseline

  7. Observations on Cortical Mechanisms for Object Recognition and Learning

    DTIC Science & Technology

    1993-12-01

    matching. iar objects such as the Eiffel Tower (M. Potter, pers. At the output of the network the activities of the vari- comm.). ous units are...with different localizations. and dendritic circuitry (see Poggio and Torre , 1978; one that could occur unsupervised and thus is similar to Torre and...5:81-100, 1990. [55] T. Poggio and V. Torre . A theory of synaptic inter- [41] H.K. Nishihara and T. Poggio. Stereo vision for actions. In W.E

  8. The impact of interactive manipulation on the recognition of objects

    NASA Astrophysics Data System (ADS)

    Meijer, Frank; van den Broek, Egon L.; Schouten, Theo

    2008-02-01

    A new application for VR has emerged: product development, in which several stakeholders (from engineers to end users) use the same VR for development and communicate purposes. Various characteristics among these stakeholders vary considerably, which imposes potential constraints to the VR. The current paper discusses the influence of three types of exploration of objects (i.e., none, passive, active) on one of these characteristics: the ability to form mental representations or visuo-spatial ability (VSA). Through an experiment we found that all users benefit from exploring objects. Moreover, people with low VSA (e.g., end users) benefit from an interactive exploration of objects opposed to people with a medium or high VSA (e.g. engineers), who are not sensitive for the type of exploration. Hence, for VR environments in which multiple stakeholders participate (e.g. for product development), differences among their cognitive abilities (e.g., VSA) have to be taken into account to enable an efficient usage of VR.

  9. Learning AND-OR templates for object recognition and detection.

    PubMed

    Si, Zhangzhang; Zhu, Song-Chun

    2013-09-01

    This paper presents a framework for unsupervised learning of a hierarchical reconfigurable image template--the AND-OR Template (AOT) for visual objects. The AOT includes: 1) hierarchical composition as "AND" nodes, 2) deformation and articulation of parts as geometric "OR" nodes, and 3) multiple ways of composition as structural "OR" nodes. The terminal nodes are hybrid image templates (HIT) [17] that are fully generative to the pixels. We show that both the structures and parameters of the AOT model can be learned in an unsupervised way from images using an information projection principle. The learning algorithm consists of two steps: 1) a recursive block pursuit procedure to learn the hierarchical dictionary of primitives, parts, and objects, and 2) a graph compression procedure to minimize model structure for better generalizability. We investigate the factors that influence how well the learning algorithm can identify the underlying AOT. And we propose a number of ways to evaluate the performance of the learned AOTs through both synthesized examples and real-world images. Our model advances the state of the art for object detection by improving the accuracy of template matching.

  10. A neuromorphic system for object detection and classification

    NASA Astrophysics Data System (ADS)

    Khosla, Deepak; Chen, Yang; Kim, Kyungnam; Cheng, Shinko Y.; Honda, Alexander L.; Zhang, Lei

    2013-05-01

    Unattended object detection, recognition and tracking on unmanned reconnaissance platforms in battlefields and urban spaces are topics of emerging importance. In this paper, we present an unattended object recognition system that automatically detects objects of interest in videos and classifies them into various categories (e.g., person, car, truck, etc.). Our system is inspired by recent findings in visual neuroscience on feed-forward object detection and recognition pipeline and mirrors that via two main neuromorphic modules (1) A front-end detection module that combines form and motion based visual attention to search for and detect "integrated" object percepts as is hypothesized to occur in the human visual pathways; (2) A back-end recognition module that processes only the detected object percepts through a neuromorphic object classification algorithm based on multi-scale convolutional neural networks, which can be efficiently implemented in COTS hardware. Our neuromorphic system was evaluated using a variety of urban area video data collected from both stationary and moving platforms. The data are quite challenging as it includes targets at long ranges, occurring under variable conditions of illuminations and occlusion with high clutter. The experimental results of our system showed excellent detection and classification performance. In addition, the proposed bio-inspired approach is good for hardware implementation due to its low complexity and mapping to off-the-shelf conventional hardware.

  11. Speech recognition system for an automotive vehicle

    SciTech Connect

    Noso, K.; Futami, T.

    1987-01-13

    A speech recognition system is described for an automotive vehicle for activating vehicle actuators in response to predetermined spoken instructions supplied to the system via a microphone, which comprises: (a) a manually controlled record switch for deriving a record signal when activated; (b) a manually controlled recognition switch for deriving a recognition signal when activated; (c) a speech recognizer for sequentially recording reference spoken instructions whenever one reference spoken instruction is supplied to the system through the microphone while the record switch is activated, a memory having a storage area for each spoken instruction, and means for shifting access to each storage area for each spoken instruction has been recorded in the storage area provided therefore. A means is included for activating vehicle actuators sequentially whenever one recognition spoken instruction is supplied to the system via the microphone while the recognition switch is activated and when the spoken instruction to be recognized is similar to the reference spoken instruction; and (d) means for deriving skip instruction signal and for coupling the skip instruction signal to the speech recognizer to shift access from a currently accessed storage area for recording a current reference spoken instruction to a succeeding storage area for recording a succeeding reference spoken instruction even when the current reference spoken instruction is not supplied to the system through the microphone.

  12. Ventral occipital lesions impair object recognition but not object-directed grasping: an fMRI study.

    PubMed

    James, Thomas W; Culham, Jody; Humphrey, G Keith; Milner, A David; Goodale, Melvyn A

    2003-11-01

    D.F., a patient with severe visual form agnosia, has been the subject of extensive research during the past decade. The fact that she could process visual input accurately for the purposes of guiding action despite being unable to perform visual discriminations on the same visual input inspired a novel interpretation of the functions of the two main cortical visual pathways or 'streams'. Within this theoretical context, the authors proposed that D.F. had suffered severe bilateral damage to her occipitotemporal visual system (the 'ventral stream'), while retaining the use of her occipitoparietal visual system (the 'dorsal stream'). The present paper reports a direct test of this idea, which was initially derived from purely behavioural data, before the advent of modern functional neuroimaging. We used functional MRI to examine activation in her ventral and dorsal streams during object recognition and object-directed grasping tasks. We found that D.F. showed no difference in activation when presented with line drawings of common objects compared with scrambled line drawings in the lateral occipital cortex (LO) of the ventral stream, an area that responded differentially to these stimuli in healthy individuals. Moreover, high-resolution anatomical MRI showed that her lesion corresponded bilaterally with the location of LO in healthy participants. The lack of activation with line drawings in D.F. mirrors her poor performance in identifying the objects depicted in the drawings. With coloured and greyscale pictures, stimuli that she can identify more often, D.F. did show some ventral-stream activation. These activations were, however, more widely distributed than those seen in control participants and did not include LO. In contrast to the absent or abnormal activation observed during these perceptual tasks, D.F. showed robust activation in the expected dorsal stream regions during object grasping, despite considerable atrophy in some regions of the parietal lobes. In

  13. Fast Object Recognition in Noisy Images Using Simulated Annealing.

    DTIC Science & Technology

    1994-12-01

    correlation coefficient is used as a measure of the match between a hypothesized object and an image. Templates are generated on-line during the search by transforming model images. Simulated annealing reduces the search time by orders of magnitude with respect to an exhaustive search. The algorithm is applied to the problem of how landmarks, for example, traffic signs, can be recognized by an autonomous vehicle or a navigating robot. The algorithm works well in noisy, real-world images of complicated scenes for model images with high information

  14. Single prolonged stress impairs social and object novelty recognition in rats.

    PubMed

    Eagle, Andrew L; Fitzpatrick, Chris J; Perrine, Shane A

    2013-11-01

    Posttraumatic stress disorder (PTSD) results from exposure to a traumatic event and manifests as re-experiencing, arousal, avoidance, and negative cognition/mood symptoms. Avoidant symptoms, as well as the newly defined negative cognitions/mood, are a serious complication leading to diminished interest in once important or positive activities, such as social interaction; however, the basis of these symptoms remains poorly understood. PTSD patients also exhibit impaired object and social recognition, which may underlie the avoidance and symptoms of negative cognition, such as social estrangement or diminished interest in activities. Previous studies have demonstrated that single prolonged stress (SPS), models PTSD phenotypes, including impairments in learning and memory. Therefore, it was hypothesized that SPS would impair social and object recognition memory. Male Sprague Dawley rats were exposed to SPS then tested in the social choice test (SCT) or novel object recognition test (NOR). These tests measure recognition of novelty over familiarity, a natural preference of rodents. Results show that SPS impaired preference for both social and object novelty. In addition, SPS impairment in social recognition may be caused by impaired behavioral flexibility, or an inability to shift behavior during the SCT. These results demonstrate that traumatic stress can impair social and object recognition memory, which may underlie certain avoidant symptoms or negative cognition in PTSD and be related to impaired behavioral flexibility.

  15. A correlation-based algorithm for recognition and tracking of partially occluded objects

    NASA Astrophysics Data System (ADS)

    Ruchay, Alexey; Kober, Vitaly

    2016-09-01

    In this work, a correlation-based algorithm consisting of a set of adaptive filters for recognition of occluded objects in still and dynamic scenes in the presence of additive noise is proposed. The designed algorithm is adaptive to the input scene, which may contain different fragments of the target, false objects, and background to be rejected. The algorithm output is high correlation peaks corresponding to pieces of the target in scenes. The proposed algorithm uses a bank of composite optimum filters. The performance of the proposed algorithm for recognition partially occluded objects is compared with that of common algorithms in terms of objective metrics.

  16. Minefield Search and Object Recognition for Autonomous Underwater Vehicles

    DTIC Science & Technology

    1992-03-01

    limitations and deep acoustic sound channel effects. Figure 7 provides a vertical comparison of AUV sonar coverage in the Straits of Bab el Mandeb and the...provide a variety of classifiable sonar data. Successful examples of expert system classifications using NPS AUV sonar data are described in detail. The...provided with complete source code.[Ref. 45] 96 3. NPS AUV Sonar Classification System The program used to implement the concepts presented in this

  17. Mangiferin, a naturally occurring glucoxilxanthone improves long-term object recognition memory in rats.

    PubMed

    Pardo Andreu, Gilberto L; Maurmann, Natasha; Reolon, Gustavo Kellermann; de Farias, Caroline B; Schwartsmann, Gilberto; Delgado, René; Roesler, Rafael

    2010-06-10

    Mangiferin (2-beta-D-glucopyranosyl-1,3,6,7-tetrahydroxyxanthone) is a xanthone widely distributed in higher plants showing antioxidative, antiviral, anticancer, antidiabetic, immunomodulatory, hepatoprotective, and analgesic effects. In the present study, we have investigated the effects of systemic administration of mangiferin on behavioral outcomes of neurological function in normal rats. A single intraperitoneal injection of mangiferin (10, 50, or 100mg/kg body weight) enhanced novel object recognition (NOR) memory when given immediately post-training. The administration of mangiferin 6h post-training did not affect NOR memory. There were no significant differences between groups in the total time exploring both objects, indicating that mangiferin did not affect locomotion or motivation. Mangiferin stimulated cell proliferation and induced a significant increase in the supernatant levels of nerve growth factor (NGF) and tumor necrosis factor (TNF)-alpha in vitro in human U138-MG glioblastoma cells. The results indicate that mangiferin enhances recognition memory through a mechanism that might involve an increase in neurotrophin and cytokine levels.

  18. Acute fasting inhibits central caspase-1 activity reducing anxiety-like behavior and increasing novel object and object location recognition.

    PubMed

    Towers, Albert E; Oelschlager, Maci L; Patel, Jay; Gainey, Stephen J; McCusker, Robert H; Freund, Gregory G

    2017-06-01

    Inflammation within the central nervous system (CNS) is frequently comorbid with anxiety. Importantly, the pro-inflammatory cytokine most commonly associated with anxiety is IL-1β. The bioavailability and activity of IL-1β are regulated by caspase-1-dependent proteolysis vis-a-vis the inflammasome. Thus, interventions regulating the activation or activity of caspase-1 should reduce anxiety especially in states that foster IL-1β maturation. Male C57BL/6j, C57BL/6j mice treated with the capase-1 inhibitor biotin-YVAD-cmk, caspase-1 knockout (KO) mice and IL-1R1 KO mice were fasted for 24h or allowed ad libitum access to food. Immediately after fasting, caspase-1 activity was measured in brain region homogenates while activated caspase-1 was localized in the brain by immunohistochemistry. Mouse anxiety-like behavior and cognition were tested using the elevated zero maze and novel object/object location tasks, respectively. A 24h fast in mice reduced the activity of caspase-1 in whole brain and in the prefrontal cortex, amygdala, hippocampus, and hypothalamus by 35%, 25%, 40%, 40%, and 40% respectively. A 24h fast also reduced anxiety-like behavior by 40% and increased novel object and object location recognition by 21% and 31%, respectively. IL-1β protein, however, was not reduced in the brain by fasting. ICV administration of YVAD decreased caspase-1 activity in the prefrontal cortex and amygdala by 55%, respectively leading to a 64% reduction in anxiety like behavior. Importantly, when caspase-1 KO or IL1-R1 KO mice are fasted, no fasting-dependent reduction in anxiety-like behavior was observed. Results indicate that fasting decrease anxiety-like behavior and improves memory by a mechanism tied to reducing caspase-1 activity throughout the brain. Copyright © 2017 Elsevier Inc. All rights reserved.

  19. An Effective 3D Shape Descriptor for Object Recognition with RGB-D Sensors

    PubMed Central

    Liu, Zhong; Zhao, Changchen; Wu, Xingming; Chen, Weihai

    2017-01-01

    RGB-D sensors have been widely used in various areas of computer vision and graphics. A good descriptor will effectively improve the performance of operation. This article further analyzes the recognition performance of shape features extracted from multi-modality source data using RGB-D sensors. A hybrid shape descriptor is proposed as a representation of objects for recognition. We first extracted five 2D shape features from contour-based images and five 3D shape features over point cloud data to capture the global and local shape characteristics of an object. The recognition performance was tested for category recognition and instance recognition. Experimental results show that the proposed shape descriptor outperforms several common global-to-global shape descriptors and is comparable to some partial-to-global shape descriptors that achieved the best accuracies in category and instance recognition. Contribution of partial features and computational complexity were also analyzed. The results indicate that the proposed shape features are strong cues for object recognition and can be combined with other features to boost accuracy. PMID:28245553

  20. Separate but interacting recognition memory systems for different senses: The role of the rat perirhinal cortex

    PubMed Central

    Albasser, Mathieu M.; Amin, Eman; Iordanova, Mihaela D.; Brown, Malcolm W.; Pearce, John M.; Aggleton, John P.

    2011-01-01

    Two different models (convergent and parallel) potentially describe how recognition memory, the ability to detect the re-occurrence of a stimulus, is organized across different senses. To contrast these two models, rats with or without perirhinal cortex lesions were compared across various conditions that controlled available information from specific sensory modalities. Intact rats not only showed visual, tactile, and olfactory recognition, but also overcame changes in the types of sensory information available between object sampling and subsequent object recognition, e.g., between sampling in the light and recognition in the dark, or vice versa. Perirhinal lesions severely impaired object recognition whenever visual cues were available, but spared olfactory recognition and tactile-based object recognition when tested in the dark. The perirhinal lesions also blocked the ability to recognize an object sampled in the light and then tested for recognition in the dark, or vice versa. The findings reveal parallel recognition systems for different senses reliant on distinct brain areas, e.g., perirhinal cortex for vision, but also show that: (1) recognition memory for multisensory stimuli involves competition between sensory systems and (2) perirhinal cortex lesions produce a bias to rely on vision, despite the presence of intact recognition memory systems serving other senses. PMID:21685150

  1. What is the role of motor simulation in action and object recognition? Evidence from apraxia.

    PubMed

    Negri, Gioia A L; Rumiati, Raffaella I; Zadini, Antonietta; Ukmar, Maja; Mahon, Bradford Z; Caramazza, Alfonso

    2007-12-01

    An important issue in contemporary cognitive neuroscience concerns the role of motor production processes in perceptual and conceptual analysis. To address this issue, we studied the performance of a large group of unilateral stroke patients across a range of tasks using the same set of common manipulable objects. All patients (n = 37) were tested for their ability to demonstrate the use of the objects, recognize the objects, recognize the corresponding object-associated pantomimes, and imitate those same pantomimes. At the group level we observed reliable correlations between object use and pantomime recognition, object use and object recognition, and pantomime imitation and pantomime recognition. At the single-case level, we document that the ability to recognize actions and objects dissociates from the ability to use those same objects. These data are problematic for the hypothesis that motor processes are constitutively involved in the recognition of actions and objects and frame new questions about the inferences that are merited by recent findings in cognitive neuroscience.

  2. License Plate Recognition System for Indian Vehicles

    NASA Astrophysics Data System (ADS)

    Sanap, P. R.; Narote, S. P.

    2010-11-01

    We consider the task of recognition of Indian vehicle number plates (also called license plates or registration plates in other countries). A system for Indian number plate recognition must cope with wide variations in the appearance of the plates. Each state uses its own range of designs with font variations between the designs. Also, vehicle owners may place the plates inside glass covered frames or use plates made of nonstandard materials. These issues compound the complexity of automatic number plate recognition, making existing approaches inadequate. We have developed a system that incorporates a novel combination of image processing and artificial neural network technologies to successfully locate and read Indian vehicle number plates in digital images. Commercial application of the system is envisaged.

  3. Scalable Medical Image Understanding by Fusing Cross-Modal Object Recognition with Formal Domain Semantics

    NASA Astrophysics Data System (ADS)

    Möller, Manuel; Sintek, Michael; Buitelaar, Paul; Mukherjee, Saikat; Zhou, Xiang Sean; Freund, Jörg

    Recent advances in medical imaging technology have dramatically increased the amount of clinical image data. In contrast, techniques for efficiently exploiting the rich semantic information in medical images have evolved much slower. Despite the research outcomes in image understanding, current image databases are still indexed by manually assigned subjective keywords instead of the semantics of the images. Indeed, most current content-based image search applications index image features that do not generalize well and use inflexible queries. This slow progress is due to the lack of scalable and generic information representation systems which can abstract over the high dimensional nature of medical images as well as semantically model the results of object recognition techniques. We propose a system combining medical imaging information with ontological formalized semantic knowledge that provides a basis for building universal knowledge repositories and gives clinicians fully cross-lingual and cross-modal access to biomedical information.

  4. First results in the development of a mobile robot with trajectory planning and object recognition capabilities

    NASA Astrophysics Data System (ADS)

    Islamgozhayev, Talgat; Kalimoldayev, Maksat; Eleusinov, Arman; Mazhitov, Shokan; Mamyrbayev, Orken

    2016-11-01

    The use of mobile robots is becoming popular in many areas of service because they ensure safety and good performance while working in dangerous or unreachable locations. Areas of application of mobile robots differ from educational research to detection of bombs and their disposal. Based on the mission of the robot they have different configurations and abilities - some of them have additional arms, cranes and other tools, others use sensors and built-in image processing and object recognition systems to perform their missions. The robot that is described in this paper is mobile robot with a turret mounted on top of it. Different approaches have been tested while searching for best method suitable for image processing and template matching goals. Based on the information from image processing unit the system executes appropriate actions for planning motions and trajectory of the mobile robot.

  5. Homotopic image pseudo-invariants for openset object recognition and image retrieval.

    PubMed

    Shinagawa, Yoshihisa

    2008-11-01

    This paper presents novel homotopic image pseudo-invariants for face recognition based on pixelwise analysis. An exemplar face and test images are matched, and the most similar image is determined first. The homotopic image pseudo-invariants are calculated next to judge whether the most similar image is the same person as the exemplar. The proposed method can be applied to openset recognition. Recognition task can be performed with or without face databases, while the recognition rate is higher when a database is available. This fact facilitates the recognition of faces and various other objects on the Internet. We benchmark the method using FERET as well as the images downloaded from the Internet.

  6. Stochastic Process Underlying Emergent Recognition of Visual Objects Hidden in Degraded Images

    PubMed Central

    Murata, Tsutomu; Hamada, Takashi; Shimokawa, Tetsuya; Tanifuji, Manabu; Yanagida, Toshio

    2014-01-01

    When a degraded two-tone image such as a “Mooney” image is seen for the first time, it is unrecognizable in the initial seconds. The recognition of such an image is facilitated by giving prior information on the object, which is known as top-down facilitation and has been intensively studied. Even in the absence of any prior information, however, we experience sudden perception of the emergence of a salient object after continued observation of the image, whose processes remain poorly understood. This emergent recognition is characterized by a comparatively long reaction time ranging from seconds to tens of seconds. In this study, to explore this time-consuming process of emergent recognition, we investigated the properties of the reaction times for recognition of degraded images of various objects. The results show that the time-consuming component of the reaction times follows a specific exponential function related to levels of image degradation and subject's capability. Because generally an exponential time is required for multiple stochastic events to co-occur, we constructed a descriptive mathematical model inspired by the neurophysiological idea of combination coding of visual objects. Our model assumed that the coincidence of stochastic events complement the information loss of a degraded image leading to the recognition of its hidden object, which could successfully explain the experimental results. Furthermore, to see whether the present results are specific to the task of emergent recognition, we also conducted a comparison experiment with the task of perceptual decision making of degraded images, which is well known to be modeled by the stochastic diffusion process. The results indicate that the exponential dependence on the level of image degradation is specific to emergent recognition. The present study suggests that emergent recognition is caused by the underlying stochastic process which is based on the coincidence of multiple stochastic events

  7. Stochastic process underlying emergent recognition of visual objects hidden in degraded images.

    PubMed

    Murata, Tsutomu; Hamada, Takashi; Shimokawa, Tetsuya; Tanifuji, Manabu; Yanagida, Toshio

    2014-01-01

    When a degraded two-tone image such as a "Mooney" image is seen for the first time, it is unrecognizable in the initial seconds. The recognition of such an image is facilitated by giving prior information on the object, which is known as top-down facilitation and has been intensively studied. Even in the absence of any prior information, however, we experience sudden perception of the emergence of a salient object after continued observation of the image, whose processes remain poorly understood. This emergent recognition is characterized by a comparatively long reaction time ranging from seconds to tens of seconds. In this study, to explore this time-consuming process of emergent recognition, we investigated the properties of the reaction times for recognition of degraded images of various objects. The results show that the time-consuming component of the reaction times follows a specific exponential function related to levels of image degradation and subject's capability. Because generally an exponential time is required for multiple stochastic events to co-occur, we constructed a descriptive mathematical model inspired by the neurophysiological idea of combination coding of visual objects. Our model assumed that the coincidence of stochastic events complement the information loss of a degraded image leading to the recognition of its hidden object, which could successfully explain the experimental results. Furthermore, to see whether the present results are specific to the task of emergent recognition, we also conducted a comparison experiment with the task of perceptual decision making of degraded images, which is well known to be modeled by the stochastic diffusion process. The results indicate that the exponential dependence on the level of image degradation is specific to emergent recognition. The present study suggests that emergent recognition is caused by the underlying stochastic process which is based on the coincidence of multiple stochastic events.

  8. From neural-based object recognition toward microelectronic eyes

    NASA Technical Reports Server (NTRS)

    Sheu, Bing J.; Bang, Sa Hyun

    1994-01-01

    Engineering neural network systems are best known for their abilities to adapt to the changing characteristics of the surrounding environment by adjusting system parameter values during the learning process. Rapid advances in analog current-mode design techniques have made possible the implementation of major neural network functions in custom VLSI chips. An electrically programmable analog synapse cell with large dynamic range can be realized in a compact silicon area. New designs of the synapse cells, neurons, and analog processor are presented. A synapse cell based on Gilbert multiplier structure can perform the linear multiplication for back-propagation networks. A double differential-pair synapse cell can perform the Gaussian function for radial-basis network. The synapse cells can be biased in the strong inversion region for high-speed operation or biased in the subthreshold region for low-power operation. The voltage gain of the sigmoid-function neurons is externally adjustable which greatly facilitates the search of optimal solutions in certain networks. Various building blocks can be intelligently connected to form useful industrial applications. Efficient data communication is a key system-level design issue for large-scale networks. We also present analog neural processors based on perceptron architecture and Hopfield network for communication applications. Biologically inspired neural networks have played an important role towards the creation of powerful intelligent machines. Accuracy, limitations, and prospects of analog current-mode design of the biologically inspired vision processing chips and cellular neural network chips are key design issues.

  9. Foreign object detection via texture recognition and a neural classifier

    NASA Astrophysics Data System (ADS)

    Patel, Devesh; Hannah, I.; Davies, E. R.

    1993-10-01

    It is rate to find pieces of stone, wood, metal, or glass in food packets, but when they occur, these foreign objects (FOs) cause distress to the consumer and concern to the manufacturer. Using x-ray imaging to detect FOs within food bags, hard contaminants such as stone or metal appear darker, whereas soft contaminants such as wood or rubber appear slightly lighter than the food substrate. In this paper we concentrate on the detection of soft contaminants such as small pieces of wood in bags of frozen corn kernels. Convolution masks are used to generate textural features which are then classified into corresponding homogeneous regions on the image using an artificial neural network (ANN) classifier. The separate ANN outputs are combined using a majority operator, and region discrepancies are removed by a median filter. Comparisons with classical classifiers showed the ANN approach to have the best overall combination of characteristics for our particular problem. The detected boundaries are in good agreement with the visually perceived segmentations.

  10. Space-object identification using spatial pattern recognition

    NASA Astrophysics Data System (ADS)

    Silversmith, Paul E.

    The traditional method of determining spacecraft attitude with a star tracker is by comparing the angle measurements between stars within a certain field-of-view (FOV) with that of angle measurements in a catalog. This technique is known as the angle method. A new approach, the planar triangle method (PTM), uses the properties of planar triangles to compare stars in a FOV with stars in a catalog. Specifically, the area and polar moment of planar triangle combinations are the comparison parameters used in the method. The PTM has been shown to provide a more consistent success rate than that of the traditional angle method. The work herein presents a technique of data association through the use of the planar triangle method. Instead of comparing the properties of stars with that of a catalog, a comparison is made between the properties of resident space objects (RSOs) and a catalog comprised of Fengyun 1C debris data and simulated data. It is shown that the planar triangle method is effective in RSO identification and is robust to the presence of measurement and sensor error.

  11. A hierarchical multiple-view approach to three-dimensional object recognition.

    PubMed

    Lin, W C; Liao, F Y; Tsao, C K; Lingutla, T

    1991-01-01

    A hierarchical approach is proposed for solving the surface and vertex correspondence problems in multiple-view-based 3D object-recognition systems. The proposed scheme is a coarse-to-fine search process, and a Hopfield network is used at each stage. Compared with conventional object-matching schemes, the proposed technique provides a more general and compact formulation of the problem and a solution more suitable for parallel implementation. At the coarse search stage, the surface matching scores between the input image and each object model in the database are computed through a Hopfield network and are used to select the candidates for further consideration. At the fine search stage, the object models selected from the previous stage are fed into another Hopfield network for vertex matching. The object model that has the best surface and vertex correspondences with the input image is finally singled out as the best matched model. Experimental results are reported using both synthetic and real range images to corroborate the proposed theory.

  12. The neural bases of crossmodal object recognition in non-human primates and rodents: a review.

    PubMed

    Cloke, Jacob M; Jacklin, Derek L; Winters, Boyer D

    2015-05-15

    The ability to integrate information from different sensory modalities to form unique multisensory object representations is a highly adaptive cognitive function. Surprisingly, non-human animal studies of the neural substrates of this form of multisensory integration have been somewhat sparse until very recently, and this may be due in part to a relative paucity of viable testing methods. Here we review the historical development and use of various "crossmodal" cognition tasks for non-human primates and rodents, focusing on tests of "crossmodal object recognition", the ability to recognize an object across sensory modalities. Such procedures have great potential to elucidate the cognitive and neural bases of object representation as it pertains to perception and memory. Indeed, these studies have revealed roles in crossmodal cognition for various brain regions (e.g., prefrontal and temporal cortices) and neurochemical systems (e.g., acetylcholine). A recent increase in behavioral and physiological studies of crossmodal cognition in rodents augurs well for the future of this research area, which should provide essential information about the basic mechanisms of object representation in the brain, in addition to fostering a better understanding of the causes of, and potential treatments for, cognitive deficits in human diseases characterized by atypical multisensory integration.

  13. Central administration of angiotensin IV rapidly enhances novel object recognition among mice.

    PubMed

    Paris, Jason J; Eans, Shainnel O; Mizrachi, Elisa; Reilley, Kate J; Ganno, Michelle L; McLaughlin, Jay P

    2013-07-01

    Angiotensin IV (Val(1)-Tyr(2)-Ile(3)-His(4)-Pro(5)-Phe(6)) has demonstrated potential cognitive-enhancing effects. The present investigation assessed and characterized: (1) dose-dependency of angiotensin IV's cognitive enhancement in a C57BL/6J mouse model of novel object recognition, (2) the time-course for these effects, (3) the identity of residues in the hexapeptide important to these effects and (4) the necessity of actions at angiotensin IV receptors for procognitive activity. Assessment of C57BL/6J mice in a novel object recognition task demonstrated that prior administration of angiotensin IV (0.1, 1.0, or 10.0, but not 0.01 nmol, i.c.v.) significantly enhanced novel object recognition in a dose-dependent manner. These effects were time dependent, with improved novel object recognition observed when angiotensin IV (0.1 nmol, i.c.v.) was administered 10 or 20, but not 30 min prior to the onset of the novel object recognition testing. An alanine scan of the angiotensin IV peptide revealed that replacement of the Val(1), Ile(3), His(4), or Phe(6) residues with Ala attenuated peptide-induced improvements in novel object recognition, whereas Tyr(2) or Pro(5) replacement did not significantly affect performance. Administration of the angiotensin IV receptor antagonist, divalinal-Ang IV (20 nmol, i.c.v.), reduced (but did not abolish) novel object recognition; however, this antagonist completely blocked the procognitive effects of angiotensin IV (0.1 nmol, i.c.v.) in this task. Rotorod testing demonstrated no locomotor effects with any angiotensin IV or divalinal-Ang IV dose tested. These data demonstrate that angiotensin IV produces a rapid enhancement of associative learning and memory performance in a mouse model that was dependent on the angiotensin IV receptor.

  14. Effects of selective neonatal hippocampal lesions on tests of object and spatial recognition memory in monkeys.

    PubMed

    Heuer, Eric; Bachevalier, Jocelyne

    2011-04-01

    Earlier studies in monkeys have reported mild impairment in recognition memory after nonselective neonatal hippocampal lesions. To assess whether the memory impairment could have resulted from damage to cortical areas adjacent to the hippocampus, we tested adult monkeys with neonatal focal hippocampal lesions and sham-operated controls in three recognition tasks: delayed nonmatching-to-sample, object memory span, and spatial memory span. Further, to rule out that normal performance on these tasks may relate to functional sparing following neonatal hippocampal lesions, we tested adult monkeys that had received the same focal hippocampal lesions in adulthood and their controls in the same three memory tasks. Both early and late onset focal hippocampal damage did not alter performance on any of the three tasks, suggesting that damage to cortical areas adjacent to the hippocampus was likely responsible for the recognition impairment reported by the earlier studies. In addition, given that animals with early and late onset hippocampal lesions showed object and spatial recognition impairment when tested in a visual paired comparison task, the data suggest that not all object and spatial recognition tasks are solved by hippocampal-dependent memory processes. The current data may not only help explain the neural substrate for the partial recognition memory impairment reported in cases of developmental amnesia, but they are also clinically relevant given that the object and spatial memory tasks used in monkeys are often translated to investigate memory functions in several populations of human infants and children in which dysfunction of the hippocampus is suspected.

  15. Expertise modulates the neural basis of context dependent recognition of objects and their relations.

    PubMed

    Bilalić, Merim; Turella, Luca; Campitelli, Guillermo; Erb, Michael; Grodd, Wolfgang

    2012-11-01

    Recognition of objects and their relations is necessary for orienting in real life. We examined cognitive processes related to recognition of objects, their relations, and the patterns they form by using the game of chess. Chess enables us to compare experts with novices and thus gain insight in the nature of development of recognition skills. Eye movement recordings showed that experts were generally faster than novices on a task that required enumeration of relations between chess objects because their extensive knowledge enabled them to immediately focus on the objects of interest. The advantage was less pronounced on random positions where the location of chess objects, and thus typical relations between them, was randomized. Neuroimaging data related experts' superior performance to the areas along the dorsal stream-bilateral posterior temporal areas and left inferior parietal lobe were related to recognition of object and their functions. The bilateral collateral sulci, together with bilateral retrosplenial cortex, were also more sensitive to normal than random positions among experts indicating their involvement in pattern recognition. The pattern of activations suggests experts engage the same regions as novices, but also that they employ novel additional regions. Expert processing, as the final stage of development, is qualitatively different than novice processing, which can be viewed as the starting stage. Since we are all experts in real life and dealing with meaningful stimuli in typical contexts, our results underline the importance of expert-like cognitive processing on generalization of laboratory results to everyday life.

  16. Dopamine D1 receptor activation leads to object recognition memory in a coral reef fish.

    PubMed

    Hamilton, Trevor J; Tresguerres, Martin; Kline, David I

    2017-07-01

    Object recognition memory is the ability to identify previously seen objects and is an adaptive mechanism that increases survival for many species throughout the animal kingdom. Previously believed to be possessed by only the highest order mammals, it is now becoming clear that fish are also capable of this type of memory formation. Similar to the mammalian hippocampus, the dorsolateral pallium regulates distinct memory processes and is modulated by neurotransmitters such as dopamine. Caribbean bicolour damselfish (Stegastes partitus) live in complex environments dominated by coral reef structures and thus likely possess many types of complex memory abilities including object recognition. This study used a novel object recognition test in which fish were first presented two identical objects, then after a retention interval of 10 min with no objects, the fish were presented with a novel object and one of the objects they had previously encountered in the first trial. We demonstrate that the dopamine D1-receptor agonist (SKF 38393) induces the formation of object recognition memories in these fish. Thus, our results suggest that dopamine-receptor mediated enhancement of spatial memory formation in fish represents an evolutionarily conserved mechanism in vertebrates. © 2017 The Author(s).

  17. Hippocampal NMDA receptors are involved in rats' spontaneous object recognition only under high memory load condition.

    PubMed

    Sugita, Manami; Yamada, Kazuo; Iguchi, Natsumi; Ichitani, Yukio

    2015-10-22

    The possible involvement of hippocampal N-methyl-D-aspartate (NMDA) receptors in spontaneous object recognition was investigated in rats under different memory load conditions. We first estimated rats' object memory span using 3-5 objects in "Different Objects Task (DOT)" in order to confirm the highest memory load condition in object recognition memory. Rats were allowed to explore a field in which 3 (3-DOT), 4 (4-DOT), or 5 (5-DOT) different objects were presented. After a delay period, they were placed again in the same field in which one of the sample objects was replaced by another object, and their object exploration behavior was analyzed. Rats could differentiate the novel object from the familiar ones in 3-DOT and 4-DOT but not in 5-DOT, suggesting that rats' object memory span was about 4. Then, we examined the effects of hippocampal AP5 infusion on performance in both 2-DOT (2 different objects were used) and 4-DOT. The drug treatment before the sample phase impaired performance only in 4-DOT. These results suggest that hippocampal NMDA receptors play a critical role in spontaneous object recognition only when the memory load is high.

  18. Sub-OBB based object recognition and localization algorithm using range images

    NASA Astrophysics Data System (ADS)

    Hoang, Dinh-Cuong; Chen, Liang-Chia; Nguyen, Thanh-Hung

    2017-02-01

    This paper presents a novel approach to recognize and estimate pose of the 3D objects in cluttered range images. The key technical breakthrough of the developed approach can enable robust object recognition and localization under undesirable condition such as environmental illumination variation as well as optical occlusion to viewing the object partially. First, the acquired point clouds are segmented into individual object point clouds based on the developed 3D object segmentation for randomly stacked objects. Second, an efficient shape-matching algorithm called Sub-OBB based object recognition by using the proposed oriented bounding box (OBB) regional area-based descriptor is performed to reliably recognize the object. Then, the 3D position and orientation of the object can be roughly estimated by aligning the OBB of segmented object point cloud with OBB of matched point cloud in a database generated from CAD model and 3D virtual camera. To detect accurate pose of the object, the iterative closest point (ICP) algorithm is used to match the object model with the segmented point clouds. From the feasibility test of several scenarios, the developed approach is verified to be feasible for object pose recognition and localization.

  19. Changes in Visual Object Recognition Precede the Shape Bias in Early Noun Learning

    PubMed Central

    Yee, Meagan; Jones, Susan S.; Smith, Linda B.

    2012-01-01

    Two of the most formidable skills that characterize human beings are language and our prowess in visual object recognition. They may also be developmentally intertwined. Two experiments, a large sample cross-sectional study and a smaller sample 6-month longitudinal study of 18- to 24-month-olds, tested a hypothesized developmental link between changes in visual object representation and noun learning. Previous findings in visual object recognition indicate that children’s ability to recognize common basic level categories from sparse structural shape representations of object shape emerges between the ages of 18 and 24 months, is related to noun vocabulary size, and is lacking in children with language delay. Other research shows in artificial noun learning tasks that during this same developmental period, young children systematically generalize object names by shape, that this shape bias predicts future noun learning, and is lacking in children with language delay. The two experiments examine the developmental relation between visual object recognition and the shape bias for the first time. The results show that developmental changes in visual object recognition systematically precede the emergence of the shape bias. The results suggest a developmental pathway in which early changes in visual object recognition that are themselves linked to category learning enable the discovery of higher-order regularities in category structure and thus the shape bias in novel noun learning tasks. The proposed developmental pathway has implications for understanding the role of specific experience in the development of both visual object recognition and the shape bias in early noun learning. PMID:23227015

  20. Changes in visual object recognition precede the shape bias in early noun learning.

    PubMed

    Yee, Meagan; Jones, Susan S; Smith, Linda B

    2012-01-01

    Two of the most formidable skills that characterize human beings are language and our prowess in visual object recognition. They may also be developmentally intertwined. Two experiments, a large sample cross-sectional study and a smaller sample 6-month longitudinal study of 18- to 24-month-olds, tested a hypothesized developmental link between changes in visual object representation and noun learning. Previous findings in visual object recognition indicate that children's ability to recognize common basic level categories from sparse structural shape representations of object shape emerges between the ages of 18 and 24 months, is related to noun vocabulary size, and is lacking in children with language delay. Other research shows in artificial noun learning tasks that during this same developmental period, young children systematically generalize object names by shape, that this shape bias predicts future noun learning, and is lacking in children with language delay. The two experiments examine the developmental relation between visual object recognition and the shape bias for the first time. The results show that developmental changes in visual object recognition systematically precede the emergence of the shape bias. The results suggest a developmental pathway in which early changes in visual object recognition that are themselves linked to category learning enable the discovery of higher-order regularities in category structure and thus the shape bias in novel noun learning tasks. The proposed developmental pathway has implications for understanding the role of specific experience in the development of both visual object recognition and the shape bias in early noun learning.

  1. A Survey on Automatic Speaker Recognition Systems

    NASA Astrophysics Data System (ADS)

    Saquib, Zia; Salam, Nirmala; Nair, Rekha P.; Pandey, Nipun; Joshi, Akanksha

    Human listeners are capable of identifying a speaker, over the telephone or an entryway out of sight, by listening to the voice of the speaker. Achieving this intrinsic human specific capability is a major challenge for Voice Biometrics. Like human listeners, voice biometrics uses the features of a person's voice to ascertain the speaker's identity. The best-known commercialized forms of voice Biometrics is Speaker Recognition System (SRS). Speaker recognition is the computing task of validating a user's claimed identity using characteristics extracted from their voices. This literature survey paper gives brief introduction on SRS, and then discusses general architecture of SRS, biometric standards relevant to voice/speech, typical applications of SRS, and current research in Speaker Recognition Systems. We have also surveyed various approaches for SRS.

  2. Representations of Shape in Object Recognition and Long-Term Visual Memory

    DTIC Science & Technology

    1993-02-11

    Pinker (1989) proposed the Multiple- Views-Plus-Transformation theory of object recognition. The foundation of this theory is th at objecto a,- represented... Pinker (1990) have shown that such shapes are immediately and consistently recognized independently of their orientation. Consequentially, throughout...along which parts may be located. Tarr and Pinker have shown that such contrasts lead to the use of orientation-dependent recognition mechanisms utilizing

  3. Vision holds a greater share in visuo-haptic object recognition than touch.

    PubMed

    Kassuba, Tanja; Klinge, Corinna; Hölig, Cordula; Röder, Brigitte; Siebner, Hartwig R

    2013-01-15

    The integration of visual and haptic input can facilitate object recognition. Yet, vision might dominate visuo-haptic interactions as it is more effective than haptics in processing several object features in parallel and recognizing objects outside of reaching space. The maximum likelihood approach of multisensory integration would predict that haptics as the less efficient sense for object recognition gains more from integrating additional visual information than vice versa. To test for asymmetries between vision and touch in visuo-haptic interactions, we measured regional changes in brain activity using functional magnetic resonance imaging while healthy individuals performed a delayed-match-to-sample task. We manipulated identity matching of sample and target objects: We hypothesized that only coherent visual and haptic object features would activate unified object representations. The bilateral object-specific lateral occipital cortex, fusiform gyrus, and intraparietal sulcus showed increased activation to crossmodal compared to unimodal matching but only for congruent object pairs. Critically, the visuo-haptic interaction effects in these regions depended on the sensory modality which processed the target object, being more pronounced for haptic than visual targets. This preferential response of visuo-haptic regions indicates a modality-specific asymmetry in crossmodal matching of visual and haptic object features, suggesting a functional primacy of vision over touch in visuo-haptic object recognition.

  4. Crowded and Sparse Domains in Object Recognition: Consequences for Categorization and Naming

    ERIC Educational Resources Information Center

    Gale, Tim M.; Laws, Keith R.; Foley, Kerry

    2006-01-01

    Some models of object recognition propose that items from structurally crowded categories (e.g., living things) permit faster access to superordinate semantic information than structurally dissimilar categories (e.g., nonliving things), but slower access to individual object information when naming items. We present four experiments that utilize…

  5. Crowded and Sparse Domains in Object Recognition: Consequences for Categorization and Naming

    ERIC Educational Resources Information Center

    Gale, Tim M.; Laws, Keith R.; Foley, Kerry

    2006-01-01

    Some models of object recognition propose that items from structurally crowded categories (e.g., living things) permit faster access to superordinate semantic information than structurally dissimilar categories (e.g., nonliving things), but slower access to individual object information when naming items. We present four experiments that utilize…

  6. Modeling guidance and recognition in categorical search: bridging human and computer object detection.

    PubMed

    Zelinsky, Gregory J; Peng, Yifan; Berg, Alexander C; Samaras, Dimitris

    2013-10-08

    Search is commonly described as a repeating cycle of guidance to target-like objects, followed by the recognition of these objects as targets or distractors. Are these indeed separate processes using different visual features? We addressed this question by comparing observer behavior to that of support vector machine (SVM) models trained on guidance and recognition tasks. Observers searched for a categorically defined teddy bear target in four-object arrays. Target-absent trials consisted of random category distractors rated in their visual similarity to teddy bears. Guidance, quantified as first-fixated objects during search, was strongest for targets, followed by target-similar, medium-similarity, and target-dissimilar distractors. False positive errors to first-fixated distractors also decreased with increasing dissimilarity to the target category. To model guidance, nine teddy bear detectors, using features ranging in biological plausibility, were trained on unblurred bears then tested on blurred versions of the same objects appearing in each search display. Guidance estimates were based on target probabilities obtained from these detectors. To model recognition, nine bear/nonbear classifiers, trained and tested on unblurred objects, were used to classify the object that would be fixated first (based on the detector estimates) as a teddy bear or a distractor. Patterns of categorical guidance and recognition accuracy were modeled almost perfectly by an HMAX model in combination with a color histogram feature. We conclude that guidance and recognition in the context of search are not separate processes mediated by different features, and that what the literature knows as guidance is really recognition performed on blurred objects viewed in the visual periphery.

  7. Modeling guidance and recognition in categorical search: Bridging human and computer object detection

    PubMed Central

    Zelinsky, Gregory J.; Peng, Yifan; Berg, Alexander C.; Samaras, Dimitris

    2013-01-01

    Search is commonly described as a repeating cycle of guidance to target-like objects, followed by the recognition of these objects as targets or distractors. Are these indeed separate processes using different visual features? We addressed this question by comparing observer behavior to that of support vector machine (SVM) models trained on guidance and recognition tasks. Observers searched for a categorically defined teddy bear target in four-object arrays. Target-absent trials consisted of random category distractors rated in their visual similarity to teddy bears. Guidance, quantified as first-fixated objects during search, was strongest for targets, followed by target-similar, medium-similarity, and target-dissimilar distractors. False positive errors to first-fixated distractors also decreased with increasing dissimilarity to the target category. To model guidance, nine teddy bear detectors, using features ranging in biological plausibility, were trained on unblurred bears then tested on blurred versions of the same objects appearing in each search display. Guidance estimates were based on target probabilities obtained from these detectors. To model recognition, nine bear/nonbear classifiers, trained and tested on unblurred objects, were used to classify the object that would be fixated first (based on the detector estimates) as a teddy bear or a distractor. Patterns of categorical guidance and recognition accuracy were modeled almost perfectly by an HMAX model in combination with a color histogram feature. We conclude that guidance and recognition in the context of search are not separate processes mediated by different features, and that what the literature knows as guidance is really recognition performed on blurred objects viewed in the visual periphery. PMID:24105460

  8. Perirhinal cortex resolves feature ambiguity in configural object recognition and perceptual oddity tasks.

    PubMed

    Bartko, Susan J; Winters, Boyer D; Cowell, Rosemary A; Saksida, Lisa M; Bussey, Timothy J

    2007-12-01

    The perirhinal cortex (PRh) has a well-established role in object recognition memory. More recent studies suggest that PRh is also important for two-choice visual discrimination tasks. Specifically, it has been suggested that PRh contains conjunctive representations that help resolve feature ambiguity, which occurs when a task cannot easily be solved on the basis of features alone. However, no study has examined whether the ability of PRh to resolve configural feature ambiguity is related to its role in object recognition. Therefore, we examined whether bilateral excitotoxic lesions of PRh or PPRh (perirhinal plus post-rhinal cortices) in the rat would cause deficits in a configural spontaneous object recognition task, and a configural simultaneous oddity discrimination task, in which the task could not be solved on the basis of features, but could only be solved using conjunctive representations. As predicted by simulations using a computational model, rats with PPRh lesions were impaired during a minimal-delay configural object recognition task. These same rats were impaired during a zero-delay configural object recognition task. Furthermore, rats with localized PRh lesions were impaired in a configural simultaneous oddity discrimination task. These findings support the idea that PRh contains conjunctive representations for the resolution of feature ambiguity and that these representations underlie a dual role for PRh in memory and perception.

  9. Intraperirhinal cortex administration of the synthetic cannabinoid, HU210, disrupts object recognition memory in rats.

    PubMed

    Sticht, Martin A; Jacklin, Derek L; Mechoulam, Raphael; Parker, Linda A; Winters, Boyer D

    2015-03-25

    Cannabinoids disrupt learning and memory in human and nonhuman participants. Object recognition memory, which is particularly susceptible to the impairing effects of cannabinoids, relies critically on the perirhinal cortex (PRh); however, to date, the effects of cannabinoids within PRh have not been assessed. In the present study, we evaluated the effects of localized administration of the synthetic cannabinoid, HU210 (0.01, 1.0 μg/hemisphere), into PRh on spontaneous object recognition in Long-Evans rats. Animals received intra-PRh infusions of HU210 before the sample phase, and object recognition memory was assessed at various delays in a subsequent retention test. We found that presample intra-PRh HU210 dose dependently (1.0 μg but not 0.01 μg) interfered with spontaneous object recognition performance, exerting an apparently more pronounced effect when memory demands were increased. These novel findings show that cannabinoid agonists in PRh disrupt object recognition memory.

  10. Contribution of the parafascicular nucleus in the spontaneous object recognition task.

    PubMed

    Castiblanco-Piñeros, Edwin; Quiroz-Padilla, Maria Fernanda; Cardenas-Palacio, Carlos Andres; Cardenas, Fernando P

    2011-09-01

    The parafascicular (PF) nucleus, a posterior component of the intralaminar nuclei of the thalamus, is considered to be an essential structure in the feedback systems of basal ganglia-thalamo-cortical circuits critically involved in cognitive processes. The specific role played by multimodal information encoded in PF neurons in learning and memory processes is still unclear. We conducted two experiments to investigate the role of the PF in the spontaneous object recognition (SOR) task. The behavioral effects of pretraining rats with bilateral lesions of PF with N-methyl-D-aspartate (NMDA) were compared to vehicle controls. In the first experiment, rats were tested on their ability to remember the association immediately after training trials and in the second experiment after a 24h delay. Our findings provide evidence that PF lesions critically affect both SOR tests and support its role in that non-spatial form of relational memory. Copyright © 2011 Elsevier Inc. All rights reserved.

  11. Object discrimination through active electrolocation: Shape recognition and the influence of electrical noise.

    PubMed

    Schumacher, Sarah; Burt de Perera, Theresa; von der Emde, Gerhard

    2016-12-12

    The weakly electric fish Gnathonemus petersii can recognise objects using active electrolocation. Here, we tested two aspects of object recognition; first whether shape recognition might be influenced by movement of the fish, and second whether object discrimination is affected by the presence of electrical noise from conspecifics. (i) Unlike other object features, such as size or volume, no parameter within a single electrical image has been found that encodes object shape. We investigated whether shape recognition might be facilitated by movement-induced modulations (MIM) of the set of electrical images that are created as a fish swims past an object. Fish were trained to discriminate between pairs of objects that either created similar or dissimilar levels of MIM of the electrical images. As predicted, the fish were able to discriminate between objects up to a longer distance if there was a large difference in MIM between the objects than if there was a small difference. This supports an involvement of MIMs in shape recognition but the use of other cues cannot be excluded. (ii) Electrical noise might impair object recognition if the noise signals overlap with the EODs of an electrolocating fish. To avoid jamming, we predicted that fish might employ pulsing strategies to prevent overlaps. To investigate the influence of electrical noise on discrimination performance, two fish were tested either in the presence of a conspecific or of playback signals and the electric signals were recorded during the experiments. The fish were surprisingly immune to jamming by conspecifics: While the discrimination performance of one fish dropped to chance level when more than 22% of its EODs overlapped with the noise signals, the performance of the other fish was not impaired even when all its EODs overlapped. Neither of the fish changed their pulsing behaviour, suggesting that they did not use any kind of jamming avoidance strategy.

  12. Grouping in object recognition: the role of a Gestalt law in letter identification.

    PubMed

    Pelli, Denis G; Majaj, Najib J; Raizman, Noah; Christian, Christopher J; Kim, Edward; Palomares, Melanie C

    2009-02-01

    The Gestalt psychologists reported a set of laws describing how vision groups elements to recognize objects. The Gestalt laws "prescribe for us what we are to recognize 'as one thing'" (Kohler, 1920). Were they right? Does object recognition involve grouping? Tests of the laws of grouping have been favourable, but mostly assessed only detection, not identification, of the compound object. The grouping of elements seen in the detection experiments with lattices and "snakes in the grass" is compelling, but falls far short of the vivid everyday experience of recognizing a familiar, meaningful, named thing, which mediates the ordinary identification of an object. Thus, after nearly a century, there is hardly any evidence that grouping plays a role in ordinary object recognition. To assess grouping in object recognition, we made letters out of grating patches and measured threshold contrast for identifying these letters in visual noise as a function of perturbation of grating orientation, phase, and offset. We define a new measure, "wiggle", to characterize the degree to which these various perturbations violate the Gestalt law of good continuation. We find that efficiency for letter identification is inversely proportional to wiggle and is wholly determined by wiggle, independent of how the wiggle was produced. Thus the effects of three different kinds of shape perturbation on letter identifiability are predicted by a single measure of goodness of continuation. This shows that letter identification obeys the Gestalt law of good continuation and may be the first confirmation of the original Gestalt claim that object recognition involves grouping.

  13. Contributions of low and high spatial frequency processing to impaired object recognition circuitry in schizophrenia.

    PubMed

    Calderone, Daniel J; Hoptman, Matthew J; Martínez, Antígona; Nair-Collins, Sangeeta; Mauro, Cristina J; Bar, Moshe; Javitt, Daniel C; Butler, Pamela D

    2013-08-01

    Patients with schizophrenia exhibit cognitive and sensory impairment, and object recognition deficits have been linked to sensory deficits. The "frame and fill" model of object recognition posits that low spatial frequency (LSF) information rapidly reaches the prefrontal cortex (PFC) and creates a general shape of an object that feeds back to the ventral temporal cortex to assist object recognition. Visual dysfunction findings in schizophrenia suggest a preferential loss of LSF information. This study used functional magnetic resonance imaging (fMRI) and resting state functional connectivity (RSFC) to investigate the contribution of visual deficits to impaired object "framing" circuitry in schizophrenia. Participants were shown object stimuli that were intact or contained only LSF or high spatial frequency (HSF) information. For controls, fMRI revealed preferential activation to LSF information in precuneus, superior temporal, and medial and dorsolateral PFC areas, whereas patients showed a preference for HSF information or no preference. RSFC revealed a lack of connectivity between early visual areas and PFC for patients. These results demonstrate impaired processing of LSF information during object recognition in schizophrenia, with patients instead displaying increased processing of HSF information. This is consistent with findings of a preference for local over global visual information in schizophrenia.

  14. Exploring tiny images: the roles of appearance and contextual information for machine and human object recognition.

    PubMed

    Parikh, Devi; Zitnick, C Lawrence; Chen, Tsuhan

    2012-10-01

    Typically, object recognition is performed based solely on the appearance of the object. However, relevant information also exists in the scene surrounding the object. In this paper, we explore the roles that appearance and contextual information play in object recognition. Through machine experiments and human studies, we show that the importance of contextual information varies with the quality of the appearance information, such as an image's resolution. Our machine experiments explicitly model context between object categories through the use of relative location and relative scale, in addition to co-occurrence. With the use of our context model, our algorithm achieves state-of-the-art performance on the MSRC and Corel data sets. We perform recognition tests for machines and human subjects on low and high resolution images, which vary significantly in the amount of appearance information present, using just the object appearance information, the combination of appearance and context, as well as just context without object appearance information (blind recognition). We also explore the impact of the different sources of context (co-occurrence, relative-location, and relative-scale). We find that the importance of different types of contextual information varies significantly across data sets such as MSRC and PASCAL.

  15. AVNG system objectives and concept

    SciTech Connect

    Macarthur, Duncan W; Thron, Jonathan; Razinkov, Sergey; Livke, Alexander; Kondratov, Sergey

    2010-01-01

    Any verification measurement performed on potentially classified nuclear material must satisfy two constraints. First and foremost, no classified information can be released to the monitoring party. At the same time, the monitoring party must gain sufficient confidence from the measurement to believe that the material being measured is consistent with the host's declarations concerning that material. The attribute measurement technique addresses both concerns by measuring several attributes of the nuclear material and displaying unclassified results through green (indicating that the material does possess the specified attribute) and red (indicating that the material does not possess the specified attribute) lights. The AVNG that we describe is an attribute measurement system built by RFNC-VNIIEF in Sarov, Russia. The AVNG measures the three attributes of 'plutonium presence,' 'plutonium mass >2 kg,' and 'plutonium isotopic ratio ({sup 240}Pu to {sup 239}Pu) <0.1' and was demonstrated in Sarov for a joint US/Russian audience in June 2009. In this presentation, we will outline the goals and objectives of the AVNG measurement system. These goals are driven by the two, sometimes conflicting, requirements mentioned above. We will describe the conceptual design of the AVNG and show how this conceptual design grew out of these goals and objectives.

  16. Automated recognition system for power quality disturbances

    NASA Astrophysics Data System (ADS)

    Abdelgalil, Tarek

    The application of deregulation policies in electric power systems has resulted in the necessity to quantify the quality of electric power. This fact highlights the need for a new monitoring strategy which is capable of tracking, detecting, classifying power quality disturbances, and then identifying the source of the disturbance. The objective of this work is to design an efficient and reliable power quality monitoring strategy that uses the advances in signal processing and pattern recognition to overcome the deficiencies that exist in power quality monitoring devices. The purposed monitoring strategy has two stages. The first stage is to detect, track, and classify any power quality violation by the use of on-line measurements. In the second stage, the source of the classified power quality disturbance must be identified. In the first stage, an adaptive linear combiner is used to detect power quality disturbances. Then, the Teager Energy Operator and Hilbert Transform are utilized for power quality event tracking. After the Fourier, Wavelet, and Walsh Transforms are employed for the feature extraction, two approaches are then exploited to classify the different power quality disturbances. The first approach depends on comparing the disturbance to be classified with a stored set of signatures for different power quality disturbances. The comparison is developed by using Hidden Markov Models and Dynamic Time Warping. The second approach depends on employing an inductive inference to generate the classification rules directly from the data. In the second stage of the new monitoring strategy, only the problem of identifying the location of the switched capacitor which initiates the transients is investigated. The Total Least Square-Estimation of Signal Parameters via Rotational Invariance Technique is adopted to estimate the amplitudes and frequencies of the various modes contained in the voltage signal measured at the facility entrance. After extracting the

  17. Rapid Pattern Recognition of Three Dimensional Objects Using Parallel Processing Within a Hierarchy of Hexagonal Grids

    NASA Astrophysics Data System (ADS)

    Tang, Haojun

    1995-01-01

    This thesis describes using parallel processing within a hierarchy of hexagonal grids to achieve rapid recognition of patterns. A seven-pixel basic hexagonal neighborhood, a sixty-one-pixel superneighborhood and pyramids of a 2-to-4 area ratio are employed. The hexagonal network achieves improved accuracy over the square network for object boundaries. The hexagonal grid with less directional sensitivity is a better approximation of the human vision grid, is more suited to natural scenes than the square grid and avoids the 4-neighbor/8-neighbor problem. Parallel processing in image analysis saves considerable time versus the traditional line-by-line method. Hexagonal parallel processing combines the optimum hexagonal geometry with the parallel structure. Our work has surveyed behavior and internal properties to construct the image on the different level of hexagonal pixel grids in a parallel computation scheme. A computer code has been developed to detect edges of digital images of real objects taken with a CCD camera within a hexagonal grid at any level. The algorithm uses the differences of the local gray level and those of its six neighbors, and is able to determine the boundary of a digital image in parallel. Also a series of algorithms and techniques have been built up to manage edge linking, feature extraction, etc. The digital images obtained from the improved CRS digital image processing system are a good approximation to the images which would be obtained with a real physical hexagonal grid. We envision that our work done within this little-known area will have some important applications in real-time machine vision. A parallel two-layer hexagonal-array retina has been designed to do pattern recognition using simple operations such as differencing, rationing, thresholding, etc. which may occur in the human retina and other biological vision systems.

  18. Object Recognition and Object Segregation in 4.5-Month-Old Infants.

    ERIC Educational Resources Information Center

    Needham, Amy

    2001-01-01

    Investigated in 6 experiments how 4.5-month-old infants' perception of a display is affected by an immediate prior experience with an object similar to part of the test display. Found that infants' use of a prior experience is disrupted by changes in the features of the object, but not by change in its spatial orientation. (JPB)

  19. Feature-specific imaging: Extensions to adaptive object recognition and active illumination based scene reconstruction

    NASA Astrophysics Data System (ADS)

    Baheti, Pawan K.

    Computational imaging (CI) systems are hybrid imagers in which the optical and post-processing sub-systems are jointly optimized to maximize the task-specific performance. In this dissertation we consider a form of CI system that measures the linear projections (i.e., features) of the scene optically, and it is commonly referred to as feature-specific imaging (FSI). Most of the previous work on FSI has been concerned with image reconstruction. Previous FSI techniques have also been non-adaptive and restricted to the use of ambient illumination. We consider two novel extensions of the FSI system in this work. We first present an adaptive feature-specific imaging (AFSI) system and consider its application to a face-recognition task. The proposed system makes use of previous measurements to adapt the projection basis at each step. We present both statistical and information-theoretic adaptation mechanisms for the AFSI system. The sequential hypothesis testing framework is used to determine the number of measurements required for achieving a specified misclassification probability. We demonstrate that AFSI system requires significantly fewer measurements than static-FSI (SFSI) and conventional imaging at low signal-to-noise ratio (SNR). We also show a trade-off, in terms of average detection time, between measurement SNR and adaptation advantage. Experimental results validating the AFSI system are presented. Next we present a FSI system based on the use of structured light. Feature measurements are obtained by projecting spatially structured illumination onto an object and collecting all of the reflected light onto a single photodetector. We refer to this system as feature-specific structured imaging (FSSI). Principal component features are used to define the illumination patterns. The optimal LMMSE operator is used to generate object estimates from the measurements. We demonstrate that this new imaging approach reduces imager complexity and provides improved image

  20. Crocins, the active constituents of Crocus sativus L., counteracted apomorphine-induced performance deficits in the novel object recognition task, but not novel object location task, in rats.

    PubMed

    Pitsikas, Nikolaos; Tarantilis, Petros A

    2017-02-17

    Schizophrenia is a chronic mental disease that affects nearly 1% of the population worldwide. Several lines of evidence suggest that the dopaminergic (DAergic) system might be compromised in schizophrenia. Specifically, the mixed dopamine (DA) D1/D2 receptor agonist apomorphine induces schizophrenia-like symptoms in rodents, including disruption of memory abilities. Crocins are among the active components of saffron (dried stigmas of Crocus sativus L. plant) and their implication in cognition is well documented. The present study investigated whether crocins counteract non-spatial and spatial recognition memory deficits induced by apomorphine in rats. For this purpose, the novel object recognition task (NORT) and the novel object location task (NOLT) were used. The effects of compounds on mobility in a locomotor activity chamber were also investigated in rats. Post-training peripheral administration of crocins (15 and 30mg/kg) counteracted apomorphine (1mg/kg)-induced performance deficits in the NORT. Conversely, crocins did not attenuate spatial recognition memory deficits produced by apomorphine in the NOLT. The present data show that crocins reversed non-spatial recognition memory impairments produced by dysfunction of the DAergic system and modulate different aspects of memory components (storage and/or retrieval). The effects of compounds on recognition memory cannot be attributed to changes in locomotor activity. Further, our findings illustrate a functional interaction between crocins and the DAergic system that may be of relevance for schizophrenia-like behavioral deficits. Therefore, the utilization of crocins as an adjunctive agent, for the treatment of cognitive deficits observed in schizophrenic patients should be further investigated.

  1. Spontaneous object recognition: a promising approach to the comparative study of memory

    PubMed Central

    Blaser, Rachel; Heyser, Charles

    2015-01-01

    Spontaneous recognition of a novel object is a popular measure of exploratory behavior, perception and recognition memory in rodent models. Because of its relative simplicity and speed of testing, the variety of stimuli that can be used, and its ecological validity across species, it is also an attractive task for comparative research. To date, variants of this test have been used with vertebrate and invertebrate species, but the methods have seldom been sufficiently standardized to allow cross-species comparison. Here, we review the methods necessary for the study of novel object recognition in mammalian and non-mammalian models, as well as the results of these experiments. Critical to the use of this test is an understanding of the organism’s initial response to a novel object, the modulation of exploration by context, and species differences in object perception and exploratory behaviors. We argue that with appropriate consideration of species differences in perception, object affordances, and natural exploratory behaviors, the spontaneous object recognition test can be a valid and versatile tool for translational research with non-mammalian models. PMID:26217207

  2. Cultural differences in visual object recognition in 3-year-old children

    PubMed Central

    Kuwabara, Megumi; Smith, Linda B.

    2016-01-01

    Recent research indicates that culture penetrates fundamental processes of perception and cognition (e.g. Nisbett & Miyamoto, 2005). Here, we provide evidence that these influences begin early and influence how preschool children recognize common objects. The three tasks (n=128) examined the degree to which nonface object recognition by 3 year olds was based on individual diagnostic features versus more configural and holistic processing. Task 1 used a 6-alternative forced choice task in which children were asked to find a named category in arrays of masked objects in which only 3 diagnostic features were visible for each object. U.S. children outperformed age-matched Japanese children. Task 2 presented pictures of objects to children piece by piece. U.S. children recognized the objects given fewer pieces than Japanese children and likelihood of recognition increased for U.S., but not Japanese children when the piece added was rated by both U.S. and Japanese adults as highly defining. Task 3 used a standard measure of configural progressing, asking the degree to which recognition of matching pictures was disrupted by the rotation of one picture. Japanese children’s recognition was more disrupted by inversion than was that of U.S. children, indicating more configural processing by Japanese than U.S. children. The pattern suggests early cross-cultural differences in visual processing; findings that raise important questions about how visual experiences differ across cultures and about universal patterns of cognitive development. PMID:26985576

  3. Orientation estimation of anatomical structures in medical images for object recognition

    NASA Astrophysics Data System (ADS)

    Bağci, Ulaş; Udupa, Jayaram K.; Chen, Xinjian

    2011-03-01

    Recognition of anatomical structures is an important step in model based medical image segmentation. It provides pose estimation of objects and information about "where" roughly the objects are in the image and distinguishing them from other object-like entities. In,1 we presented a general method of model-based multi-object recognition to assist in segmentation (delineation) tasks. It exploits the pose relationship that can be encoded, via the concept of ball scale (b-scale), between the binary training objects and their associated grey images. The goal was to place the model, in a single shot, close to the right pose (position, orientation, and scale) in a given image so that the model boundaries fall in the close vicinity of object boundaries in the image. Unlike position and scale parameters, we observe that orientation parameters require more attention when estimating the pose of the model as even small differences in orientation parameters can lead to inappropriate recognition. Motivated from the non-Euclidean nature of the pose information, we propose in this paper the use of non-Euclidean metrics to estimate orientation of the anatomical structures for more accurate recognition and segmentation. We statistically analyze and evaluate the following metrics for orientation estimation: Euclidean, Log-Euclidean, Root-Euclidean, Procrustes Size-and-Shape, and mean Hermitian metrics. The results show that mean Hermitian and Cholesky decomposition metrics provide more accurate orientation estimates than other Euclidean and non-Euclidean metrics.

  4. Retrieval and reconsolidation of object recognition memory are independent processes in the perirhinal cortex.

    PubMed

    Balderas, I; Rodriguez-Ortiz, C J; Bermudez-Rattoni, F

    2013-12-03

    Reconsolidation refers to the destabilization/re-stabilization process upon memory reactivation. However, the parameters needed to induce reconsolidation remain unclear. Here we evaluated the capacity of memory retrieval to induce reconsolidation of object recognition memory in rats. To assess whether retrieval is indispensable to trigger reconsolidation, we injected muscimol in the perirhinal cortex to block retrieval, and anisomycin (ani) to impede reconsolidation. We observed that ani impaired reconsolidation in the absence of retrieval. Therefore, stored memory underwent reconsolidation even though it was not recalled. These results indicate that retrieval and reconsolidation of object recognition memory are independent processes.

  5. Recognition of partially occluded threat objects using the annealed Hopefield network

    NASA Technical Reports Server (NTRS)

    Kim, Jung H.; Yoon, Sung H.; Park, Eui H.; Ntuen, Celestine A.

    1992-01-01

    Recognition of partially occluded objects has been an important issue to airport security because occlusion causes significant problems in identifying and locating objects during baggage inspection. The neural network approach is suitable for the problems in the sense that the inherent parallelism of neural networks pursues many hypotheses in parallel resulting in high computation rates. Moreover, they provide a greater degree of robustness or fault tolerance than conventional computers. The annealed Hopfield network which is derived from the mean field annealing (MFA) has been developed to find global solutions of a nonlinear system. In the study, it has been proven that the system temperature of MFA is equivalent to the gain of the sigmoid function of a Hopfield network. In our early work, we developed the hybrid Hopfield network (HHN) for fast and reliable matching. However, HHN doesn't guarantee global solutions and yields false matching under heavily occluded conditions because HHN is dependent on initial states by its nature. In this paper, we present the annealed Hopfield network (AHN) for occluded object matching problems. In AHN, the mean field theory is applied to the hybird Hopfield network in order to improve computational complexity of the annealed Hopfield network and provide reliable matching under heavily occluded conditions. AHN is slower than HHN. However, AHN provides near global solutions without initial restrictions and provides less false matching than HHN. In conclusion, a new algorithm based upon a neural network approach was developed to demonstrate the feasibility of the automated inspection of threat objects from x-ray images. The robustness of the algorithm is proved by identifying occluded target objects with large tolerance of their features.

  6. On the three-quarter view advantage of familiar object recognition.

    PubMed

    Nonose, Kohei; Niimi, Ryosuke; Yokosawa, Kazuhiko

    2016-11-01

    A three-quarter view, i.e., an oblique view, of familiar objects often leads to a higher subjective goodness rating when compared with other orientations. What is the source of the high goodness for oblique views? First, we confirmed that object recognition performance was also best for oblique views around 30° view, even when the foreshortening disadvantage of front- and side-views was minimized (Experiments 1 and 2). In Experiment 3, we measured subjective ratings of view goodness and two possible determinants of view goodness: familiarity of view, and subjective impression of three-dimensionality. Three-dimensionality was measured as the subjective saliency of visual depth information. The oblique views were rated best, most familiar, and as approximating greatest three-dimensionality on average; however, the cluster analyses showed that the "best" orientation systematically varied among objects. We found three clusters of objects: front-preferred objects, oblique-preferred objects, and side-preferred objects. Interestingly, recognition performance and the three-dimensionality rating were higher for oblique views irrespective of the clusters. It appears that recognition efficiency is not the major source of the three-quarter view advantage. There are multiple determinants and variability among objects. This study suggests that the classical idea that a canonical view has a unique advantage in object perception requires further discussion.

  7. Object recognition in congruent and incongruent natural scenes: a life-span study.

    PubMed

    Rémy, F; Saint-Aubert, L; Bacon-Macé, N; Vayssière, N; Barbeau, E; Fabre-Thorpe, M

    2013-10-18

    Efficient processing of our complex visual environment is essential and many daily visual tasks rely on accurate and fast object recognition. It is therefore important to evaluate how object recognition performance evolves during the course of adulthood. Surprisingly, this ability has not yet been investigated in the aged population, although several neuroimaging studies have reported altered activity in high-level visual ventral regions when elderly subjects process natural stimuli. In the present study, color photographs of various objects embedded in contextual scenes were used to assess object categorization performance in 97 participants aged from 20 to 91. Objects were either animals or pieces of furniture, embedded in either congruent or incongruent contexts. In every age group, subjects showed reduced categorization performance, both in terms of accuracy and speed, when objects were seen in incongruent vs. congruent contexts. In subjects over 60 years old, object categorization was greatly slowed down when compared to young and middle-aged subjects. Moreover, subjects over 75 years old evidenced a significant decrease in categorization accuracy when objects were seen in incongruent contexts. This indicates that incongruence of the scene may be particularly disturbing in late adulthood, therefore impairing object recognition. Our results suggest that daily visual processing of complex natural environments may be less efficient with age, which might impact performance in everyday visual tasks.

  8. Ontogeny of object versus location recognition in the rat: acquisition and retention effects.

    PubMed

    Westbrook, Sara R; Brennan, Lauren E; Stanton, Mark E

    2014-11-01

    Novel object and location recognition tasks harness the rat's natural tendency to explore novelty (Berlyne, 1950) to study incidental learning. The present study examined the ontogenetic profile of these two tasks and retention of spatial learning between postnatal day (PD) 17 and 31. Experiment 1 showed that rats ages PD17, 21, and 26 recognize novel objects, but only PD21 and PD26 rats recognize a novel location of a familiar object. These results suggest that novel object recognition develops before PD17, while object location recognition emerges between PD17 and PD21. Experiment 2 studied the ontogenetic profile of object location memory retention in PD21, 26, and 31 rats. PD26 and PD31 rats retained the object location memory for both 10-min and 24-hr delays. PD21 rats failed to retain the object location memory for the 24-hr delay, suggesting differential development of short- versus long-term memory in the ontogeny of object location memory.

  9. A neuromorphic architecture for object recognition and motion anticipation using burst-STDP.

    PubMed

    Nere, Andrew; Olcese, Umberto; Balduzzi, David; Tononi, Giulio

    2012-01-01

    In this work we investigate the possibilities offered by a minimal framework of artificial spiking neurons to be deployed in silico. Here we introduce a hierarchical network architecture of spiking neurons which learns to recognize moving objects in a visual environment and determine the correct motor output for each object. These tasks are learned through both supervised and unsupervised spike timing dependent plasticity (STDP). STDP is responsible for the strengthening (or weakening) of synapses in relation to pre- and post-synaptic spike times and has been described as a Hebbian paradigm taking place both in vitro and in vivo. We utilize a variation of STDP learning, called burst-STDP, which is based on the notion that, since spikes are expensive in terms of energy consumption, then strong bursting activity carries more information than single (sparse) spikes. Furthermore, this learning algorithm takes advantage of homeostatic renormalization, which has been hypothesized to promote memory consolidation during NREM sleep. Using this learning rule, we design a spiking neural network architecture capable of object recognition, motion detection, attention towards important objects, and motor control outputs. We demonstrate the abilities of our design in a simple environment with distractor objects, multiple objects moving concurrently, and in the presence of noise. Most importantly, we show how this neural network is capable of performing these tasks using a simple leaky-integrate-and-fire (LIF) neuron model with binary synapses, making it fully compatible with state-of-the-art digital neuromorphic hardware designs. As such, the building blocks and learning rules presented in this paper appear promising for scalable fully neuromorphic systems to be implemented in hardware chips.

  10. A Neuromorphic Architecture for Object Recognition and Motion Anticipation Using Burst-STDP

    PubMed Central

    Balduzzi, David; Tononi, Giulio

    2012-01-01

    In this work we investigate the possibilities offered by a minimal framework of artificial spiking neurons to be deployed in silico. Here we introduce a hierarchical network architecture of spiking neurons which learns to recognize moving objects in a visual environment and determine the correct motor output for each object. These tasks are learned through both supervised and unsupervised spike timing dependent plasticity (STDP). STDP is responsible for the strengthening (or weakening) of synapses in relation to pre- and post-synaptic spike times and has been described as a Hebbian paradigm taking place both in vitro and in vivo. We utilize a variation of STDP learning, called burst-STDP, which is based on the notion that, since spikes are expensive in terms of energy consumption, then strong bursting activity carries more information than single (sparse) spikes. Furthermore, this learning algorithm takes advantage of homeostatic renormalization, which has been hypothesized to promote memory consolidation during NREM sleep. Using this learning rule, we design a spiking neural network architecture capable of object recognition, motion detection, attention towards important objects, and motor control outputs. We demonstrate the abilities of our design in a simple environment with distractor objects, multiple objects moving concurrently, and in the presence of noise. Most importantly, we show how this neural network is capable of performing these tasks using a simple leaky-integrate-and-fire (LIF) neuron model with binary synapses, making it fully compatible with state-of-the-art digital neuromorphic hardware designs. As such, the building blocks and learning rules presented in this paper appear promising for scalable fully neuromorphic systems to be implemented in hardware chips. PMID:22615855

  11. Joint Segmentation and Recognition of Categorized Objects from Noisy Web Image Collection.

    PubMed

    Wang, Le; Hua, Gang; Xue, Jianru; Gao, Zhanning; Zheng, Nanning

    2014-07-14

    The segmentation of categorized objects addresses the problem of joint segmentation of a single category of object across a collection of images, where categorized objects are referred to objects in the same category. Most existing methods of segmentation of categorized objects made the assumption that all images in the given image collection contain the target object. In other words, the given image collection is noise free. Therefore, they may not work well when there are some noisy images which are not in the same category, such as those image collections gathered by a text query from modern image search engines. To overcome this limitation, we propose a method for automatic segmentation and recognition of categorized objects from noisy Web image collections. This is achieved by cotraining an automatic object segmentation algorithm that operates directly on a collection of images, and an object category recognition algorithm that identifies which images contain the target object. The object segmentation algorithm is trained on a subset of images from the given image collection which are recognized to contain the target object with high confidence, while training the object category recognition model is guided by the intermediate segmentation results obtained from the object segmentation algorithm. This way, our co-training algorithm automatically identifies the set of true positives in the noisy Web image collection, and simultaneously extracts the target objects from all the identified images. Extensive experiments validated the efficacy of our proposed approach on four datasets: 1) the Weizmann horse dataset, 2) the MSRC object category dataset, 3) the iCoseg dataset, and 4) a new 30-categories dataset including 15,634 Web images with both hand-annotated category labels and ground truth segmentation labels. It is shown that our method compares favorably with the state-of-the-art, and has the ability to deal with noisy image collections.

  12. Securing iris recognition systems against masquerade attacks

    NASA Astrophysics Data System (ADS)

    Galbally, Javier; Gomez-Barrero, Marta; Ross, Arun; Fierrez, Julian; Ortega-Garcia, Javier

    2013-05-01

    A novel two-stage protection scheme for automatic iris recognition systems against masquerade attacks carried out with synthetically reconstructed iris images is presented. The method uses different characteristics of real iris images to differentiate them from the synthetic ones, thereby addressing important security flaws detected in state-of-the-art commercial systems. Experiments are carried out on the publicly available Biosecure Database and demonstrate the efficacy of the proposed security enhancing approach.

  13. A roadmap to global illumination in 3D scenes: solutions for GPU object recognition